Trust in Artificial Intelligent Agents Scale

First quantitative approbation. Data analysis workflow

Anton Angelgardt

HSE University

2021-05-15


Preprocess

Find preprocess workflow here.

Packages

library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(psych)
## 
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
## 
##     %+%, alpha
library(lavaan)
## This is lavaan 0.6-8
## lavaan is FREE software! Please report any bugs.
## 
## Attaching package: 'lavaan'
## The following object is masked from 'package:psych':
## 
##     cor2cov
library(semPlot)
library(knitr)
library(corrplot)
## corrplot 0.84 loaded
theme_set(theme_bw())

Import data

taia <- read_csv("https://github.com/angelgardt/taia/raw/master/data/taia.csv")
## 
## ── Column specification ────────────────────────────────────────────────────────
## cols(
##   .default = col_double(),
##   id = col_character(),
##   oth_text = col_character(),
##   expoth_text = col_character(),
##   sex = col_character(),
##   edulvl1 = col_character(),
##   spec1 = col_character(),
##   edulvl2 = col_character(),
##   spec2 = col_character(),
##   jobfield = col_character(),
##   jobpos = col_character(),
##   city = col_character()
## )
## ℹ Use `spec()` for the full column specifications.
str(taia)
## tibble [495 × 133] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ id         : chr [1:495] "00XzIUUVmQ" "0aABrq9MBY" "0c6myGTrKr" "0CS5iaAVos" ...
##  $ e_dighelp  : num [1:495] 5 NA 4 3.33 3 ...
##  $ n_dighelp  : num [1:495] 1 NA 1 3 2 1 3 2 4 1 ...
##  $ e_socnet   : num [1:495] 0 NA 3.2 3.6 4.5 ...
##  $ f_socnet   : num [1:495] 3 NA 2.4 1.6 2 ...
##  $ n_socnet   : num [1:495] 2 NA 5 5 2 2 2 4 3 4 ...
##  $ gt_score   : num [1:495] 2.67 2.67 2.83 2.5 2.67 ...
##  $ pr01       : num [1:495] 3 3 3 3 3 4 3 1 3 4 ...
##  $ pr02       : num [1:495] 3 3 3 3 3 3 3 1 3 3 ...
##  $ pr03       : num [1:495] 3 3 3 3 3 1 5 1 3 4 ...
##  $ pr04       : num [1:495] 2 3 3 3 2 0 3 2 4 3 ...
##  $ pr05       : num [1:495] 3 2 1 2 3 4 4 1 0 3 ...
##  $ pr06       : num [1:495] 2 2 4 3 3 5 4 3 4 4 ...
##  $ pr07       : num [1:495] 3 3 3 3 3 5 3 2 1 3 ...
##  $ pr08       : num [1:495] 2 3 4 2 3 4 4 4 3 4 ...
##  $ pr09       : num [1:495] 2 4 3 3 4 4 4 3 3 4 ...
##  $ pr10       : num [1:495] 2 3 3 2 3 4 3 3 1 3 ...
##  $ co01       : num [1:495] 2 3 3 2 3 4 3 2 4 3 ...
##  $ co02       : num [1:495] 3 3 3 2 3 3 3 1 2 3 ...
##  $ co03       : num [1:495] 3 4 4 2 3 4 4 2 2 3 ...
##  $ co04       : num [1:495] 4 2 4 4 3 5 4 3 5 4 ...
##  $ co05       : num [1:495] 2 2 3 2 3 4 4 2 3 2 ...
##  $ co06       : num [1:495] 3 3 4 4 3 3 4 2 2 3 ...
##  $ co07       : num [1:495] 2 3 1 1 1 1 1 3 0 1 ...
##  $ co08       : num [1:495] 2 2 2 1 4 5 2 1 2 1 ...
##  $ co09       : num [1:495] 2 3 2 1 4 4 3 2 1 2 ...
##  $ co10       : num [1:495] 3 2 3 2 3 5 3 1 1 2 ...
##  $ ut01       : num [1:495] 3 4 4 5 4 5 5 4 4 3 ...
##  $ ut02       : num [1:495] 2 3 3 4 4 5 5 3 3 3 ...
##  $ ut03       : num [1:495] 3 2 4 5 1 5 3 4 3 3 ...
##  $ ut04       : num [1:495] 3 3 3 4 4 5 4 3 2 3 ...
##  $ ut05       : num [1:495] 3 2 3 5 4 3 4 3 4 3 ...
##  $ ut06       : num [1:495] 2 3 4 4 4 5 4 3 3 3 ...
##  $ ut07       : num [1:495] 3 2 4 5 4 4 4 3 4 3 ...
##  $ ut08       : num [1:495] 3 3 3 4 4 5 4 3 4 4 ...
##  $ ut09       : num [1:495] 2 3 3 3 3 4 4 3 3 4 ...
##  $ ut10       : num [1:495] 2 2 2 4 1 2 2 1 3 3 ...
##  $ ut11       : num [1:495] 2 2 3 4 3 2 4 1 1 3 ...
##  $ ut12       : num [1:495] 3 4 4 3 4 2 4 3 3 4 ...
##  $ fa01       : num [1:495] 2 2 3 4 2 2 3 3 2 2 ...
##  $ fa02       : num [1:495] 2 3 2 4 2 0 2 3 2 1 ...
##  $ fa03       : num [1:495] 3 3 3 1 4 2 1 0 3 2 ...
##  $ fa04       : num [1:495] 2 3 3 2 1 2 2 0 1 2 ...
##  $ fa05       : num [1:495] 3 3 3 3 4 4 3 3 2 3 ...
##  $ fa06       : num [1:495] 3 2 4 3 3 2 4 0 2 3 ...
##  $ fa07       : num [1:495] 3 3 3 3 1 3 2 1 1 3 ...
##  $ fa08       : num [1:495] 3 2 2 2 1 2 2 3 2 2 ...
##  $ fa09       : num [1:495] 3 2 3 4 2 1 2 3 2 2 ...
##  $ fa10       : num [1:495] 2 2 2 4 1 3 3 4 4 2 ...
##  $ de01       : num [1:495] 3 2 3 3 3 3 4 3 3 3 ...
##  $ de02       : num [1:495] 3 3 3 3 3 4 4 2 1 3 ...
##  $ de03       : num [1:495] 3 3 4 3 3 5 3 2 1 3 ...
##  $ de04       : num [1:495] 2 3 2 0 2 2 0 3 1 3 ...
##  $ de05       : num [1:495] 3 3 4 3 3 5 5 4 4 4 ...
##  $ de06       : num [1:495] 2 3 3 3 3 3 4 0 0 3 ...
##  $ de07       : num [1:495] 3 2 3 3 3 3 4 3 3 3 ...
##  $ de08       : num [1:495] 3 3 3 3 3 5 4 1 1 3 ...
##  $ de09       : num [1:495] 4 2 3 3 3 5 5 4 1 4 ...
##  $ de10       : num [1:495] 3 3 4 3 3 3 4 3 3 3 ...
##  $ de11       : num [1:495] 2 3 2 3 2 1 4 4 1 1 ...
##  $ un01       : num [1:495] 3 3 3 2 4 3 4 3 4 4 ...
##  $ un02       : num [1:495] 2 2 3 2 4 3 4 2 3 3 ...
##  $ un03       : num [1:495] 3 1 3 3 4 5 4 2 4 3 ...
##  $ un04       : num [1:495] 3 1 3 3 4 3 3 2 4 3 ...
##  $ un05       : num [1:495] 3 3 4 3 4 4 4 3 4 4 ...
##  $ un06       : num [1:495] 3 3 2 1 1 1 4 1 4 4 ...
##  $ un07       : num [1:495] 2 3 2 2 4 4 3 1 2 3 ...
##  $ un08       : num [1:495] 2 3 3 3 4 4 4 4 4 3 ...
##  $ un09       : num [1:495] 2 1 4 2 4 4 4 1 2 4 ...
##  $ un10       : num [1:495] 3 3 3 2 4 3 4 2 2 4 ...
##  $ un11       : num [1:495] 3 2 3 2 4 4 3 3 4 3 ...
##  $ un12       : num [1:495] 3 2 3 3 4 4 4 3 4 3 ...
##  $ gt01       : num [1:495] 3 3 3 2 3 2 1 1 1 2 ...
##  $ gt02       : num [1:495] 3 2 3 3 3 3 1 1 1 2 ...
##  $ gt03       : num [1:495] 3 3 3 3 3 2 1 1 1 3 ...
##  $ gt04       : num [1:495] 3 2 3 2 3 4 1 1 2 2 ...
##  $ gt05       : num [1:495] 2 3 2 2 1 4 0 2 0 2 ...
##  $ gt06       : num [1:495] 2 3 3 3 3 3 3 1 1 3 ...
##  $ socnet     : num [1:495] 1 0 1 1 1 1 1 1 1 1 ...
##  $ vk         : num [1:495] 1 -2 1 1 1 1 1 1 1 1 ...
##  $ fb         : num [1:495] 0 -2 1 1 1 0 0 1 0 1 ...
##  $ tw         : num [1:495] 0 -2 1 0 0 0 0 0 0 0 ...
##  $ in         : num [1:495] 1 -2 1 1 0 1 1 1 1 1 ...
##  $ tt         : num [1:495] 0 -2 0 1 0 0 0 0 0 0 ...
##  $ yt         : num [1:495] 0 -2 1 1 0 0 0 1 1 1 ...
##  $ freqvk     : num [1:495] 3 -2 3 2 3 3 3 3 3 3 ...
##  $ freqfb     : num [1:495] -2 -2 2 2 1 -2 -2 0 -2 3 ...
##  $ freqtw     : num [1:495] -2 -2 2 -2 -2 -2 -2 -2 -2 -2 ...
##  $ freqin     : num [1:495] 3 -2 3 1 -2 3 3 2 3 3 ...
##  $ freqtt     : num [1:495] -2 -2 -2 1 -2 -2 -2 -2 -2 -2 ...
##  $ freqyt     : num [1:495] -2 -2 2 2 -2 -2 -2 2 2 3 ...
##  $ expvk      : num [1:495] 0 -2 4 3 5 3 5 4 3 3 ...
##  $ expfb      : num [1:495] -2 -2 3 3 4 -2 -2 2 -2 2 ...
##  $ exptw      : num [1:495] -2 -2 2 -2 -2 -2 -2 -2 -2 -2 ...
##  $ expin      : num [1:495] 0 -2 4 4 -2 4 5 2 2 4 ...
##  $ exptt      : num [1:495] -2 -2 -2 4 -2 -2 -2 -2 -2 -2 ...
##  $ expyt      : num [1:495] -2 -2 3 4 -2 -2 -2 4 2 3 ...
##  $ dighelp    : num [1:495] 1 0 1 1 1 1 1 1 1 1 ...
##  $ siri       : num [1:495] 0 -2 0 1 0 0 1 0 1 0 ...
##   [list output truncated]
##  - attr(*, "spec")=
##   .. cols(
##   ..   id = col_character(),
##   ..   e_dighelp = col_double(),
##   ..   n_dighelp = col_double(),
##   ..   e_socnet = col_double(),
##   ..   f_socnet = col_double(),
##   ..   n_socnet = col_double(),
##   ..   gt_score = col_double(),
##   ..   pr01 = col_double(),
##   ..   pr02 = col_double(),
##   ..   pr03 = col_double(),
##   ..   pr04 = col_double(),
##   ..   pr05 = col_double(),
##   ..   pr06 = col_double(),
##   ..   pr07 = col_double(),
##   ..   pr08 = col_double(),
##   ..   pr09 = col_double(),
##   ..   pr10 = col_double(),
##   ..   co01 = col_double(),
##   ..   co02 = col_double(),
##   ..   co03 = col_double(),
##   ..   co04 = col_double(),
##   ..   co05 = col_double(),
##   ..   co06 = col_double(),
##   ..   co07 = col_double(),
##   ..   co08 = col_double(),
##   ..   co09 = col_double(),
##   ..   co10 = col_double(),
##   ..   ut01 = col_double(),
##   ..   ut02 = col_double(),
##   ..   ut03 = col_double(),
##   ..   ut04 = col_double(),
##   ..   ut05 = col_double(),
##   ..   ut06 = col_double(),
##   ..   ut07 = col_double(),
##   ..   ut08 = col_double(),
##   ..   ut09 = col_double(),
##   ..   ut10 = col_double(),
##   ..   ut11 = col_double(),
##   ..   ut12 = col_double(),
##   ..   fa01 = col_double(),
##   ..   fa02 = col_double(),
##   ..   fa03 = col_double(),
##   ..   fa04 = col_double(),
##   ..   fa05 = col_double(),
##   ..   fa06 = col_double(),
##   ..   fa07 = col_double(),
##   ..   fa08 = col_double(),
##   ..   fa09 = col_double(),
##   ..   fa10 = col_double(),
##   ..   de01 = col_double(),
##   ..   de02 = col_double(),
##   ..   de03 = col_double(),
##   ..   de04 = col_double(),
##   ..   de05 = col_double(),
##   ..   de06 = col_double(),
##   ..   de07 = col_double(),
##   ..   de08 = col_double(),
##   ..   de09 = col_double(),
##   ..   de10 = col_double(),
##   ..   de11 = col_double(),
##   ..   un01 = col_double(),
##   ..   un02 = col_double(),
##   ..   un03 = col_double(),
##   ..   un04 = col_double(),
##   ..   un05 = col_double(),
##   ..   un06 = col_double(),
##   ..   un07 = col_double(),
##   ..   un08 = col_double(),
##   ..   un09 = col_double(),
##   ..   un10 = col_double(),
##   ..   un11 = col_double(),
##   ..   un12 = col_double(),
##   ..   gt01 = col_double(),
##   ..   gt02 = col_double(),
##   ..   gt03 = col_double(),
##   ..   gt04 = col_double(),
##   ..   gt05 = col_double(),
##   ..   gt06 = col_double(),
##   ..   socnet = col_double(),
##   ..   vk = col_double(),
##   ..   fb = col_double(),
##   ..   tw = col_double(),
##   ..   `in` = col_double(),
##   ..   tt = col_double(),
##   ..   yt = col_double(),
##   ..   freqvk = col_double(),
##   ..   freqfb = col_double(),
##   ..   freqtw = col_double(),
##   ..   freqin = col_double(),
##   ..   freqtt = col_double(),
##   ..   freqyt = col_double(),
##   ..   expvk = col_double(),
##   ..   expfb = col_double(),
##   ..   exptw = col_double(),
##   ..   expin = col_double(),
##   ..   exptt = col_double(),
##   ..   expyt = col_double(),
##   ..   dighelp = col_double(),
##   ..   siri = col_double(),
##   ..   alice = col_double(),
##   ..   salut = col_double(),
##   ..   oleg = col_double(),
##   ..   alex = col_double(),
##   ..   mia = col_double(),
##   ..   mts = col_double(),
##   ..   ggle = col_double(),
##   ..   oth = col_double(),
##   ..   oth_text = col_character(),
##   ..   expsiri = col_double(),
##   ..   expalice = col_double(),
##   ..   expsalut = col_double(),
##   ..   expoleg = col_double(),
##   ..   expalex = col_double(),
##   ..   expmia = col_double(),
##   ..   expmts = col_double(),
##   ..   expggle = col_double(),
##   ..   expoth = col_double(),
##   ..   expoth_text = col_character(),
##   ..   selfdrcar = col_double(),
##   ..   selfdrexp = col_double(),
##   ..   selfdrsafe = col_double(),
##   ..   eduai = col_double(),
##   ..   eduaiexp = col_double(),
##   ..   age = col_double(),
##   ..   sex = col_character(),
##   ..   edulvl1 = col_character(),
##   ..   spec1 = col_character(),
##   ..   edu2 = col_double(),
##   ..   edulvl2 = col_character(),
##   ..   spec2 = col_character(),
##   ..   jobfield = col_character(),
##   ..   jobpos = col_character(),
##   ..   city = col_character()
##   .. )

Preparation

Vectors of TAIA items:

pr_items <- colnames(taia)[8:17]
co_items <- colnames(taia)[18:27]
ut_items <- colnames(taia)[28:39]
fa_items <- colnames(taia)[40:49]
de_items <- colnames(taia)[50:60]
un_items <- colnames(taia)[61:72]
taia_items <- colnames(taia)[8:72]

Vector of GT items:

gt_items <- colnames(taia)[73:78]

Column names for further formatting:

col_names <- c("", "Num. of obs.", "Mean", "SD",
               "Median", "Trimmed Mean", "MAD",
               "Min", "Max", "Range",
               "Skewness", "Kurtuosis", "SE")
total_colnames <- c("Alpha", "Standardized Alpha", "Guttman's Lambda 6",
                    "Average interitem correlation", "S/N",
                    "Alpha SE", "Scale Mean", "Total Score SD",
                    "Median interitem correlation")
item_stats_colnames <- c("Num. of Obs.", "Discrimination",
                         "Std Cor",
                         "Cor Overlap Corrected",
                         "Cor if drop",
                         "Difficulty", "SD")
alpha_drop_colnames <- c("Alpha", "Standardized Alpha",
                "Guttman's Lambda 6",   "Average interitem correlation",
                "S/N",  "Alpha SE", "Var(r)","Median interitem correlation")

Exploratory analysis

TAIA descriptive statistics

taia %>% 
  select(all_of(pr_items)) %>% 
  describe() %>% 
  kable(caption = "Predictability", label = 1, digits = 2, col.names = col_names)
Predictability
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
pr01 1 495 2.84 0.99 3 2.87 1.48 0 5 5 -0.28 0.37 0.04
pr02 2 495 2.73 0.97 3 2.77 1.48 0 5 5 -0.19 0.10 0.04
pr03 3 495 2.89 1.01 3 2.91 1.48 0 5 5 -0.15 -0.05 0.05
pr04 4 495 2.84 1.04 3 2.87 1.48 0 5 5 -0.18 -0.04 0.05
pr05 5 495 2.22 1.20 2 2.22 1.48 0 5 5 0.03 -0.31 0.05
pr06 6 495 3.04 1.07 3 3.06 1.48 0 5 5 -0.26 0.07 0.05
pr07 7 495 2.59 1.11 3 2.61 1.48 0 5 5 -0.15 -0.10 0.05
pr08 8 495 3.05 0.91 3 3.09 0.00 0 5 5 -0.56 1.26 0.04
pr09 9 495 2.89 0.95 3 2.94 0.00 0 5 5 -0.50 1.05 0.04
pr10 10 495 2.83 1.04 3 2.90 1.48 0 5 5 -0.41 0.28 0.05
taia %>% select(all_of(pr_items)) %>% 
  pivot_longer(cols = all_of(pr_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "darkred") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Predictability") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • pr01 OK
    • Я считаю, что интеллектуальные системы надежны
  • pr02 OK
    • Я считаю, что результаты работы интеллектуальных систем хорошо предсказуемы
  • pr03 OK
    • Я считаю, что интеллектуальные системы ненадежны (R)
  • pr04 OK
    • Я считаю, что результаты работы интеллектуальных систем невозможно предсказать (R)
  • pr05 positive skewness
    • Я считаю, что поездки в машине, управляемой искусственным интеллектом, безопаснее, чем в обычной
  • pr06 OK
    • Я считаю, что медицинская диагностика с применением интеллектуальных систем надеждее, чем без них
  • pr07 OK
    • Я считаю, что финансовые операции под контролем искусственного интеллекта безопаснее, чем обычные
  • pr08 high kurtosis
    • Я считаю, что интеллектуальные системы, обеспечивающие безопасность домов, хорошо справляются со своей задачей
  • pr09 high kurtosis
    • Я считаю, что рекомендательные системы чаще всего правильно определяют предпочтения пользователей
  • pr10 OK
taia %>% 
  select(all_of(co_items)) %>% 
  describe() %>% 
  kable(caption = "Consistency", label = 2, digits = 2, col.names = col_names)
Consistency
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
co01 1 495 2.49 1.08 3 2.51 1.48 0 5 5 -0.17 0.13 0.05
co02 2 495 2.51 1.04 3 2.53 1.48 0 5 5 -0.19 -0.06 0.05
co03 3 495 2.86 1.02 3 2.92 1.48 0 5 5 -0.40 0.31 0.05
co04 4 495 3.47 1.09 4 3.54 1.48 0 5 5 -0.57 0.32 0.05
co05 5 495 2.20 1.11 2 2.17 1.48 0 5 5 0.10 -0.17 0.05
co06 6 495 2.52 1.11 3 2.53 1.48 0 5 5 -0.13 -0.15 0.05
co07 7 495 1.59 1.13 2 1.52 1.48 0 5 5 0.54 0.12 0.05
co08 8 495 1.90 1.04 2 1.86 1.48 0 5 5 0.40 0.28 0.05
co09 9 495 2.05 1.07 2 2.01 1.48 0 5 5 0.35 0.12 0.05
co10 10 495 2.44 1.10 2 2.44 1.48 0 5 5 -0.04 -0.06 0.05
taia %>% select(all_of(co_items)) %>% 
  pivot_longer(cols = all_of(co_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "chocolate3") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Consistency") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • co01 OK
    • Интеллектуальные системы надежны, так как те системы, с которыми я сталкивался (сталкивалась), были надежными
  • co02 OK
    • Я считаю, что если система при тестировании работает корректно, то и дальше она будет работать корректно
  • co03 high kurtosis
    • Я считаю, что интеллектуальные системы совершают меньше технических ошибок, чем люди
  • co04 high negative skewness
    • Со временем любая интеллектуальная система будет совершать всё меньше ошибок
  • co05 positive skewness
    • Если интеллектуальные системы, с которыми я сталкивался (сталкивалась), были надежными, то я могу считать надёжными другие системы
  • co06 positive skewness
    • Я могу судить о надёжности новой интеллектуальной системы по опыту работы с другими системами
  • co07 high positive skewness
    • Я могу сказать, что система работает корректно, только протестировав её (R)
  • co08 positive skewness
    • Если одна интеллектуальная система подводит меня, то и с другими будет то же самое
  • co09positive skewness
    • Если одна интеллектуальная система соответствует моим ожиданиям, то с другими будет то же самое
  • co10 positive skewness
    • Я могу сформировать ожидания относительно работы интеллектуальных систем в целом на основе опыта взаимодействия с одной системой
taia %>% 
  select(all_of(ut_items)) %>% 
  describe() %>% 
  kable(caption = "Utility", label = 3, digits = 2, col.names = col_names)
Utility
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
ut01 1 495 3.78 1.05 4 3.88 1.48 0 5 5 -0.86 1.12 0.05
ut02 2 495 3.52 1.05 3 3.59 1.48 0 5 5 -0.53 0.50 0.05
ut03 3 495 3.56 1.11 4 3.64 1.48 0 5 5 -0.57 0.15 0.05
ut04 4 495 3.09 1.11 3 3.15 1.48 0 5 5 -0.43 0.03 0.05
ut05 5 495 3.05 1.21 3 3.09 1.48 0 5 5 -0.33 -0.15 0.05
ut06 6 495 3.27 1.10 3 3.31 1.48 0 5 5 -0.61 0.68 0.05
ut07 7 495 3.20 1.13 3 3.23 1.48 0 5 5 -0.28 -0.22 0.05
ut08 8 495 3.44 1.05 3 3.49 1.48 0 5 5 -0.55 0.44 0.05
ut09 9 495 3.18 1.17 3 3.23 1.48 0 5 5 -0.47 0.16 0.05
ut10 10 495 2.17 1.11 2 2.16 1.48 0 5 5 0.08 -0.23 0.05
ut11 11 495 2.67 1.23 3 2.69 1.48 0 5 5 -0.11 -0.41 0.06
ut12 12 495 3.16 1.15 3 3.21 1.48 0 5 5 -0.42 0.03 0.05
taia %>% select(all_of(ut_items)) %>% 
  pivot_longer(cols = all_of(ut_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "goldenrod3") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Utility") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • ut01 extremely high negative skewness
    • Я считаю, что интеллектуальные технологии — неотъемлемая часть развития общества
  • ut02 high negative skewness
    • Я считаю, что человечество нуждается в интеллектуальных системах
  • ut03 high negative skewness
    • Мне кажется, человечеству будет лучше без интеллектуальных систем (R)
  • ut04 negative skewness
    • Я считаю, что развитие интеллектуальных систем — это оправданный риск для общества
  • ut05 OK
    • По моему мнению, без интеллектуальных систем общественный прогресс остановился бы
  • ut06 negative skewness
    • Я считаю, что интеллектуальные системы существенно повышают качество медицинской диагностики
  • ut07 light negative skewness
    • Мне кажется, что оформить услуги с цифровыми помощниками гораздо проще, чем без них
  • ut08 negative skewness
    • Мне кажется, рекомендательные сервисы существенно сокращают время поиска нужной информации
  • ut09 negative skewness
    • Я считаю, что если полиция будет использовать интеллектуальные системы, то количество раскрытых преступлений увеличится
  • ut10 positive skewness
    • Мне кажется, при оформлении услуг через интернет можно справиться и без цифровых помощников (R)
  • ut11 OK
    • Я считаю, что если на дорогах появятся машины, управляемые искусственным интеллектом, то число аварий снизится
  • ut12 negative skewness
    • Я считаю, что использование интеллектуальных систем в обучении повышает качество образования
taia %>% 
  select(all_of(fa_items)) %>% 
  describe() %>% 
  kable(caption = "Faith", label = 4, digits = 2, col.names = col_names)
Faith
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
fa01 1 495 2.42 1.10 2 2.42 1.48 0 5 5 -0.02 -0.29 0.05
fa02 2 495 2.16 1.18 2 2.15 1.48 0 5 5 0.18 -0.42 0.05
fa03 3 495 1.51 1.13 1 1.42 1.48 0 5 5 0.66 0.16 0.05
fa04 4 495 1.57 1.08 1 1.51 1.48 0 5 5 0.55 0.17 0.05
fa05 5 495 2.46 1.10 2 2.48 1.48 0 5 5 -0.15 -0.10 0.05
fa06 6 495 2.47 1.08 3 2.49 1.48 0 5 5 -0.18 0.06 0.05
fa07 7 495 2.37 1.09 2 2.38 1.48 0 5 5 -0.14 -0.17 0.05
fa08 8 495 2.21 1.14 2 2.17 1.48 0 5 5 0.28 -0.13 0.05
fa09 9 495 2.29 1.18 2 2.27 1.48 0 5 5 0.15 -0.40 0.05
fa10 10 495 2.64 1.20 3 2.62 1.48 0 5 5 0.06 -0.28 0.05
taia %>% select(all_of(fa_items)) %>% 
  pivot_longer(cols = all_of(fa_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "darkgreen") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Faith") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • fa01 OK
    • Я готов (готова) довериться интеллектуальным системам, даже если я не до конца понимаю, как они работают
  • fa02 light positive skewness
    • Чтобы доверять интеллектуальной системе, мне нужно точно понимать, как работают её алгоритмы (R)
  • fa03 hard positive skewness
    • Если интеллектуальная система перестает реагировать на запросы, мне с этим комфортно
  • fa04 hard positive skewness
    • Если интеллектуальная система управлениями финансами не реагирует на запросы, я все равно буду уверен, что она работает корректно
  • fa05 OK
    • Я готов (готова) доверять результатам работы интеллектуальных систем, даже если я не знаю, как они работают
  • fa06 OK
    • Я готов (готова) довериться работе интеллектуальных систем так же, как работе профессионалов
  • fa07 OK
    • Я предпочту сам (сама) контролировать весь процесс нежели дам контроль интеллектуальной системе (R)
  • fa08 light positive skewness
    • Мне нужно знать детали работы алгоритма, чтобы быть уверенным (уверенной) в качестве результата его работы (R)
  • fa09 OK
    • Если я не понимаю, как работает интеллектуальная система, я не могу быть уверенным (уверенной) в результате её работы (R)
  • fa10 OK
    • Мне не важно, как работает интеллектуальная система, если она должным образом справляется со своей задачей
taia %>% 
  select(all_of(de_items)) %>% 
  describe() %>% 
  kable(caption = "Dependability", label = 5, digits = 2, col.names = col_names)
Dependability
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
de01 1 495 2.59 1.10 3 2.64 1.48 0 5 5 -0.42 0.08 0.05
de02 2 495 2.17 1.15 2 2.18 1.48 0 5 5 0.00 -0.34 0.05
de03 3 495 2.17 1.19 2 2.17 1.48 0 5 5 0.04 -0.30 0.05
de04 4 495 1.90 1.05 2 1.85 1.48 0 5 5 0.55 0.66 0.05
de05 5 495 3.57 1.16 4 3.68 1.48 0 5 5 -0.78 0.48 0.05
de06 6 495 2.23 1.23 2 2.25 1.48 0 5 5 0.01 -0.43 0.06
de07 7 495 2.82 1.00 3 2.86 1.48 0 5 5 -0.30 0.31 0.04
de08 8 495 2.65 1.06 3 2.70 1.48 0 5 5 -0.40 0.14 0.05
de09 9 495 3.44 1.20 4 3.54 1.48 0 5 5 -0.61 -0.14 0.05
de10 10 495 2.25 1.18 2 2.28 1.48 0 5 5 -0.22 -0.42 0.05
de11 11 495 2.31 1.20 2 2.31 1.48 0 5 5 0.00 -0.52 0.05
taia %>% select(all_of(de_items)) %>% 
  pivot_longer(cols = all_of(de_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "darkblue") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Dependability") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • de01 negative skewness
    • Я готов (готова) следовать рекомендациям рекомендательных систем социальных сетей
  • de02 OK
    • Я готов (готова) делегировать управление финансами интеллектуальному помощнику
  • de03 OK
    • Если интеллектуальная система запрашивает мои личные данные, я могу быть уверен (уверенна) в их сохранности
  • de04 hard positive skewness
    • Я могу доверять интеллектуальной системе, если я точно понимаю, какие опасности исходят от неё
  • de05 hard negative skewness
    • Я бы мог (могла) жить в «умном доме»
  • de06 negative kurtosis
    • Если бы я ехал (ехала) в автомобиле, управляемом искусственным интеллектом, я бы был спокоен за свою безопасность
  • de07 OK
    • Если меня обследуют с помощью интеллектуальных медицинских технологий, я могу доверять выставленному диагнозу
  • de08 OK
    • Я считаю, что при покупках с интеллектуальными помощниками риск ошибиться меньше, чем без них
  • de09 negative skewness
    • Мне было бы некомфортно жить в «умном доме» (R)
  • de10 negative kurtosis
    • Я могу доверить искусственному интеллекту задачи, от которых зависит моя личная безопасность
  • de11 negative kurtosis
    • Я могу доверить искусственному интеллекту только рутинные задачи (например, уборка) (R)
taia %>%
  select(all_of(un_items)) %>% 
  describe() %>% 
  kable(caption = "Understanding", label = 6, digits = 2, col.names = col_names)
Understanding
Num. of obs. Mean SD Median Trimmed Mean MAD Min Max Range Skewness Kurtuosis SE
un01 1 495 2.93 1.05 3 3.01 1.48 0 5 5 -0.48 0.31 0.05
un02 2 495 2.47 1.14 3 2.49 1.48 0 5 5 -0.17 -0.27 0.05
un03 3 495 3.02 1.17 3 3.10 1.48 0 5 5 -0.55 0.01 0.05
un04 4 495 2.61 1.09 3 2.65 1.48 0 5 5 -0.33 -0.22 0.05
un05 5 495 2.82 1.10 3 2.90 1.48 0 5 5 -0.51 0.24 0.05
un06 6 495 2.29 1.23 2 2.26 1.48 0 5 5 0.19 -0.62 0.06
un07 7 495 2.13 1.18 2 2.14 1.48 0 5 5 -0.02 -0.54 0.05
un08 8 495 2.90 1.16 3 2.96 1.48 0 5 5 -0.45 0.00 0.05
un09 9 495 2.32 1.23 2 2.37 1.48 0 5 5 -0.18 -0.75 0.06
un10 10 495 2.24 1.15 2 2.23 1.48 0 5 5 0.05 -0.44 0.05
un11 11 495 2.63 1.20 3 2.66 1.48 0 5 5 -0.25 -0.37 0.05
un12 12 495 2.89 1.12 3 2.96 1.48 0 5 5 -0.46 0.13 0.05
taia %>% select(all_of(un_items)) %>% 
  pivot_longer(cols = all_of(un_items)) %>% 
  ggplot(aes(value)) +
  geom_bar(fill = "purple4") +
  facet_wrap(~ name) +
  scale_x_discrete(limits = 0:5) +
  labs(x = "Score", y = "Number of observations",
       title = "Understanding") +
  theme(plot.title = element_text(hjust = .5))
## Warning: Continuous limits supplied to discrete scale.
## Did you mean `limits = factor(...)` or `scale_*_continuous()`?

  • un01 OK
    • Я понимаю, как происходит взаимодействие человека с интеллектуальными системами
  • un02 OK
    • Я понимаю, как работают алгоритмы интеллектуальных систем
  • un03 negative skewness
    • Я стараюсь разобраться в том, как работают интеллектуальные системы
  • un04 negative skewness
    • Я понимаю, как работают отдельные элементы интеллектуальных систем
  • un05 positive kurtosis
    • Я понимаю общий принцип работы интеллектуальных систем
  • un06 negative kurtosis
    • Я плохо разбираюсь в тонкостях работы интеллектуальных систем (R)
  • un07 negative kurtosis
    • Мне понятно, как работают интеллектуальные алгоритмы, применяемые в медицинской диагностике
  • un08 OK
    • Мне понятно, как работают алгоритмы рекомендательных систем социальных сетей
  • un09 extra negative kurtosis
    • Я понимаю, как работают алгоритмы автомобилей, управляемых искусственным интеллектом
  • un10 negative kurtosis
    • Я понимаю, как работают алгоритмы интеллектуальных систем, которые управляют финансами
  • un11 OK
    • Мне понятно, как устроены алгоритмы машинного перевода текстов
  • un12 OK
    • Мне понятно, как работают алгоритмы систем типа «умный дом»

Correlations

Predictability

corrplot.mixed(cor(taia %>% select(all_of(pr_items))),
               lower.col = "black")

Consistency

corrplot.mixed(cor(taia %>% select(all_of(co_items))),
               lower.col = "black")

Utility

corrplot.mixed(cor(taia %>% select(all_of(ut_items))),
               lower.col = "black")

Faith

corrplot.mixed(cor(taia %>% select(all_of(fa_items))),
               lower.col = "black")

Dependability

corrplot.mixed(cor(taia %>% select(all_of(de_items))),
               lower.col = "black")

Understanding

corrplot.mixed(cor(taia %>% select(all_of(un_items))),
               lower.col = "black")

All TAIA items correlations

qgraph::qgraph(
  cor(taia %>% select(all_of(taia_items))),
  layout = "spring",
  posCol = "darkgreen",
  negCol = "darkred"
)

Psychometric Analysis

Subscales

Predictability

pr1 <- psych::alpha(
  taia %>% select(all_of(pr_items)),
  cumulative = TRUE,
  title = "Predictability Factor",
  check.keys = FALSE
)
kable(pr1$total,
      caption = "Perdictability. Subscale statistics", 
      label = 7, digits = 2,
      col.names = total_colnames
      )
Perdictability. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.81 0.81 0.82 0.3 4.25 0.01 27.92 6.23 0.33
pr1$item.stats$mean <- pr1$item.stats$mean / 5
kable(pr1$item.stats,
      caption = "Predictability. Items statistics",
      label = 8, digits = 2,
      col.names = item_stats_colnames)
Predictability. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
pr01 495 0.79 0.80 0.80 0.72 0.57 0.99
pr02 495 0.66 0.66 0.62 0.56 0.55 0.97
pr03 495 0.45 0.45 0.37 0.31 0.58 1.01
pr04 495 0.32 0.32 0.21 0.16 0.57 1.04
pr05 495 0.61 0.59 0.51 0.46 0.44 1.20
pr06 495 0.62 0.62 0.56 0.50 0.61 1.07
pr07 495 0.74 0.73 0.70 0.63 0.52 1.11
pr08 495 0.72 0.73 0.71 0.64 0.61 0.91
pr09 495 0.61 0.62 0.56 0.50 0.58 0.95
pr10 495 0.55 0.56 0.47 0.42 0.57 1.04
pr1$item.stats %>%
  ggplot(aes(x = row.names(pr1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Predictability. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(pr1$alpha.drop,
      caption = "Predictability. Subscale statistics when item drop",
      label = 9, digits = 2, col.names = alpha_drop_colnames)
Predictability. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
pr01 0.76 0.77 0.78 0.27 3.27 0.02 0.02 0.29
pr02 0.78 0.79 0.80 0.29 3.66 0.01 0.03 0.32
pr03 0.81 0.81 0.81 0.32 4.33 0.01 0.03 0.36
pr04 0.82 0.83 0.82 0.35 4.78 0.01 0.02 0.36
pr05 0.79 0.80 0.81 0.30 3.88 0.01 0.03 0.33
pr06 0.79 0.79 0.81 0.30 3.79 0.01 0.03 0.33
pr07 0.77 0.78 0.79 0.28 3.46 0.02 0.02 0.30
pr08 0.77 0.78 0.79 0.28 3.46 0.02 0.02 0.30
pr09 0.79 0.79 0.80 0.30 3.80 0.01 0.03 0.35
pr10 0.80 0.80 0.81 0.31 3.99 0.01 0.03 0.35
kable(pr1$response.freq,
      caption = "Predictability. Non missing response frequency for each item",
      label = 10, digits = 2)
Predictability. Non missing response frequency for each item
0 1 2 3 4 5 miss
pr01 0.02 0.06 0.24 0.45 0.19 0.04 0
pr02 0.01 0.08 0.28 0.43 0.17 0.03 0
pr03 0.01 0.06 0.26 0.40 0.22 0.05 0
pr04 0.02 0.07 0.27 0.38 0.21 0.05 0
pr05 0.09 0.17 0.33 0.29 0.09 0.03 0
pr06 0.02 0.06 0.20 0.41 0.23 0.08 0
pr07 0.04 0.12 0.28 0.38 0.14 0.04 0
pr08 0.02 0.03 0.16 0.52 0.24 0.04 0
pr09 0.02 0.05 0.18 0.53 0.17 0.04 0
pr10 0.02 0.08 0.21 0.45 0.20 0.04 0

Consistency

co1 <- psych::alpha(
  taia %>% select(all_of(co_items)),
  cumulative = TRUE,
  title = "Consistency Factor",
  check.keys = FALSE
)
## Warning in psych::alpha(taia %>% select(all_of(co_items)), cumulative = TRUE, : Some items were negatively correlated with the total scale and probably 
## should be reversed.  
## To do this, run the function again with the 'check.keys=TRUE' option
## Some items ( co07 ) were negatively correlated with the total scale and 
## probably should be reversed.  
## To do this, run the function again with the 'check.keys=TRUE' option
kable(co1$total,
      caption = "Consistency. Subscale statistics", 
      label = 11, digits = 2,
      col.names = total_colnames)
Consistency. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.76 0.77 0.8 0.25 3.27 0.01 24.03 6.1 0.27
co1$item.stats$mean <- co1$item.stats$mean / 5
kable(co1$item.stats,
      caption = "Consistency. Items statistics",
      label = 12, digits = 2,
      col.names = item_stats_colnames)
Consistency. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
co01 495 0.74 0.74 0.72 0.64 0.50 1.08
co02 495 0.68 0.69 0.65 0.57 0.50 1.04
co03 495 0.55 0.55 0.48 0.41 0.57 1.02
co04 495 0.40 0.41 0.30 0.24 0.69 1.09
co05 495 0.79 0.78 0.79 0.70 0.44 1.11
co06 495 0.65 0.65 0.61 0.53 0.50 1.11
co07 495 -0.03 -0.04 -0.22 -0.22 0.32 1.13
co08 495 0.45 0.46 0.36 0.30 0.38 1.04
co09 495 0.76 0.77 0.76 0.67 0.41 1.07
co10 495 0.67 0.67 0.62 0.56 0.49 1.10
co1$item.stats %>%
  ggplot(aes(x = row.names(co1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Consistency. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(co1$alpha.drop,
      caption = "Consistency. Subscale statistics when item drop",
      label = 13, digits = 2,
      col.names = alpha_drop_colnames)
Consistency. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
co01 0.71 0.72 0.76 0.22 2.52 0.02 0.06 0.26
co02 0.72 0.73 0.77 0.23 2.66 0.02 0.06 0.26
co03 0.74 0.75 0.79 0.25 2.98 0.02 0.07 0.27
co04 0.77 0.77 0.80 0.27 3.36 0.01 0.06 0.35
co05 0.70 0.71 0.75 0.21 2.42 0.02 0.06 0.26
co06 0.73 0.73 0.77 0.23 2.74 0.02 0.06 0.27
co07 0.83 0.82 0.83 0.34 4.70 0.01 0.03 0.36
co08 0.76 0.76 0.79 0.26 3.23 0.02 0.07 0.34
co09 0.71 0.71 0.75 0.22 2.47 0.02 0.06 0.26
co10 0.72 0.73 0.77 0.23 2.69 0.02 0.07 0.26
kable(co1$response.freq,
      caption = "Consistency. Non missing response frequency for each item",
      label = 14, digits = 2)
Consistency. Non missing response frequency for each item
0 1 2 3 4 5 miss
co01 0.05 0.11 0.31 0.39 0.11 0.03 0
co02 0.03 0.12 0.32 0.38 0.13 0.02 0
co03 0.02 0.07 0.22 0.44 0.21 0.04 0
co04 0.01 0.04 0.10 0.35 0.32 0.18 0
co05 0.06 0.19 0.37 0.27 0.09 0.02 0
co06 0.04 0.14 0.28 0.38 0.13 0.03 0
co07 0.18 0.31 0.32 0.14 0.04 0.02 0
co08 0.08 0.27 0.42 0.16 0.06 0.01 0
co09 0.06 0.24 0.40 0.22 0.06 0.02 0
co10 0.04 0.14 0.33 0.34 0.11 0.03 0

Utility

ut1 <- psych::alpha(
  taia %>% select(all_of(ut_items)),
  cumulative = TRUE,
  title = "Utility Factor",
  check.keys = FALSE
)
kable(ut1$total,
      caption = "Utility. Subscale statistics", 
      label = 15, digits = 2,
      col.names = total_colnames)
Utility. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.86 0.86 0.87 0.34 6.17 0.01 38.09 8.44 0.37
ut1$item.stats$mean <- ut1$item.stats$mean / 5
kable(ut1$item.stats,
      caption = "Utility. Items statistics",
      label = 16, digits = 2,
      col.names = item_stats_colnames)
Utility. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
ut01 495 0.77 0.78 0.78 0.71 0.76 1.05
ut02 495 0.82 0.83 0.84 0.77 0.70 1.05
ut03 495 0.57 0.57 0.52 0.47 0.71 1.11
ut04 495 0.51 0.51 0.44 0.40 0.62 1.11
ut05 495 0.69 0.69 0.65 0.61 0.61 1.21
ut06 495 0.76 0.76 0.74 0.70 0.65 1.10
ut07 495 0.63 0.63 0.59 0.54 0.64 1.13
ut08 495 0.65 0.66 0.62 0.57 0.69 1.05
ut09 495 0.68 0.68 0.64 0.59 0.64 1.17
ut10 495 0.17 0.17 0.06 0.04 0.43 1.11
ut11 495 0.56 0.55 0.48 0.45 0.53 1.23
ut12 495 0.71 0.71 0.68 0.64 0.63 1.15
ut1$item.stats %>%
  ggplot(aes(x = row.names(ut1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Utility. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(ut1$alpha.drop,
      caption = "Utility. Subscale statistics when item drop",
      label = 17, digits = 2,
      col.names = alpha_drop_colnames)
Utility. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
ut01 0.84 0.84 0.85 0.32 5.16 0.01 0.03 0.34
ut02 0.83 0.83 0.84 0.31 5.00 0.01 0.03 0.33
ut03 0.85 0.85 0.86 0.35 5.84 0.01 0.04 0.41
ut04 0.86 0.86 0.87 0.36 6.06 0.01 0.03 0.41
ut05 0.84 0.84 0.86 0.33 5.45 0.01 0.04 0.37
ut06 0.84 0.84 0.85 0.32 5.21 0.01 0.03 0.33
ut07 0.85 0.85 0.86 0.34 5.65 0.01 0.04 0.37
ut08 0.85 0.85 0.86 0.34 5.55 0.01 0.03 0.37
ut09 0.84 0.85 0.86 0.33 5.49 0.01 0.03 0.37
ut10 0.88 0.88 0.88 0.40 7.40 0.01 0.01 0.41
ut11 0.85 0.86 0.87 0.35 5.92 0.01 0.04 0.41
ut12 0.84 0.84 0.86 0.33 5.37 0.01 0.03 0.35
kable(ut1$response.freq,
      caption = "Utility. Non missing response frequency for each item",
      label = 18, digits = 2)
Utility. Non missing response frequency for each item
0 1 2 3 4 5 miss
ut01 0.01 0.01 0.06 0.29 0.34 0.28 0
ut02 0.01 0.02 0.09 0.38 0.30 0.20 0
ut03 0.01 0.04 0.09 0.33 0.31 0.22 0
ut04 0.02 0.08 0.15 0.40 0.27 0.09 0
ut05 0.03 0.06 0.20 0.35 0.23 0.12 0
ut06 0.03 0.03 0.13 0.39 0.30 0.12 0
ut07 0.01 0.05 0.19 0.35 0.26 0.14 0
ut08 0.01 0.03 0.11 0.36 0.34 0.15 0
ut09 0.03 0.05 0.15 0.38 0.25 0.13 0
ut10 0.07 0.19 0.37 0.26 0.09 0.02 0
ut11 0.05 0.12 0.27 0.32 0.18 0.07 0
ut12 0.02 0.07 0.15 0.38 0.26 0.12 0

Faith

fa1 <- psych::alpha(
  taia %>% select(all_of(fa_items)),
  cumulative = TRUE,
  title = "Faith Factor",
  check.keys = FALSE
)
kable(fa1$total,
      caption = "Faith. Subscale statistics", 
      label = 19, digits = 2,
      col.names = total_colnames)
Faith. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.77 0.77 0.81 0.25 3.26 0.02 22.1 6.41 0.24
fa1$item.stats$mean <- fa1$item.stats$mean / 5
kable(fa1$item.stats,
      caption = "Faith. Items statistics",
      label = 20, digits = 2,
      col.names = item_stats_colnames)
Faith. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
fa01 495 0.76 0.76 0.76 0.67 0.48 1.10
fa02 495 0.61 0.60 0.56 0.47 0.43 1.18
fa03 495 0.27 0.28 0.16 0.10 0.30 1.13
fa04 495 0.41 0.42 0.33 0.26 0.31 1.08
fa05 495 0.77 0.78 0.78 0.69 0.49 1.10
fa06 495 0.55 0.56 0.50 0.42 0.49 1.08
fa07 495 0.42 0.42 0.31 0.26 0.47 1.09
fa08 495 0.58 0.57 0.52 0.44 0.44 1.14
fa09 495 0.66 0.65 0.62 0.53 0.46 1.18
fa10 495 0.63 0.62 0.57 0.50 0.53 1.20
fa1$item.stats %>%
  ggplot(aes(x = row.names(fa1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Faith. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(fa1$alpha.drop,
      caption = "Faith. Subscale statistics when item drop",
      label = 21, digits = 2,
      col.names = alpha_drop_colnames)
Faith. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
fa01 0.71 0.71 0.76 0.22 2.47 0.02 0.04 0.22
fa02 0.74 0.74 0.78 0.24 2.87 0.02 0.04 0.24
fa03 0.79 0.79 0.82 0.29 3.70 0.01 0.04 0.30
fa04 0.77 0.77 0.81 0.27 3.30 0.02 0.04 0.26
fa05 0.71 0.71 0.76 0.21 2.43 0.02 0.04 0.22
fa06 0.75 0.75 0.79 0.25 2.95 0.02 0.05 0.29
fa07 0.77 0.77 0.81 0.27 3.30 0.02 0.05 0.30
fa08 0.74 0.75 0.79 0.25 2.92 0.02 0.04 0.24
fa09 0.73 0.73 0.78 0.23 2.73 0.02 0.04 0.24
fa10 0.74 0.74 0.79 0.24 2.79 0.02 0.04 0.24
kable(fa1$response.freq,
      caption = "Faith. Non missing response frequency for each item",
      label = 22, digits = 2)
Faith. Non missing response frequency for each item
0 1 2 3 4 5 miss
fa01 0.04 0.16 0.32 0.33 0.13 0.03 0
fa02 0.08 0.21 0.36 0.21 0.12 0.02 0
fa03 0.19 0.35 0.29 0.11 0.05 0.01 0
fa04 0.16 0.34 0.33 0.12 0.04 0.01 0
fa05 0.05 0.12 0.33 0.34 0.13 0.03 0
fa06 0.05 0.12 0.32 0.38 0.11 0.03 0
fa07 0.05 0.15 0.32 0.35 0.11 0.02 0
fa08 0.05 0.20 0.38 0.23 0.10 0.03 0
fa09 0.06 0.19 0.34 0.25 0.13 0.03 0
fa10 0.04 0.12 0.31 0.32 0.14 0.08 0

Dependability

de1 <- psych::alpha(
  taia %>% select(all_of(de_items)),
  cumulative = TRUE,
  title = "Dependability Factor",
  check.keys = FALSE
)
## Warning in psych::alpha(taia %>% select(all_of(de_items)), cumulative = TRUE, : Some items were negatively correlated with the total scale and probably 
## should be reversed.  
## To do this, run the function again with the 'check.keys=TRUE' option
## Some items ( de04 ) were negatively correlated with the total scale and 
## probably should be reversed.  
## To do this, run the function again with the 'check.keys=TRUE' option
kable(de1$total,
      caption = "Dependability. Subscale statistics", 
      label = 23, digits = 2,
      col.names = total_colnames)
Dependability. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.75 0.75 0.8 0.21 2.96 0.02 28.09 6.74 0.24
de1$item.stats$mean <- de1$item.stats$mean / 5
kable(de1$item.stats,
      caption = "Dependability. Items statistics",
      label = 24, digits = 2,
      col.names = item_stats_colnames)
Dependability. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
de01 495 0.57 0.58 0.52 0.45 0.52 1.10
de02 495 0.72 0.72 0.69 0.61 0.43 1.15
de03 495 0.66 0.66 0.61 0.54 0.43 1.19
de04 495 -0.23 -0.22 -0.39 -0.36 0.38 1.05
de05 495 0.59 0.58 0.56 0.46 0.71 1.16
de06 495 0.67 0.67 0.62 0.55 0.45 1.23
de07 495 0.58 0.60 0.54 0.47 0.56 1.00
de08 495 0.67 0.68 0.66 0.57 0.53 1.06
de09 495 0.45 0.44 0.39 0.30 0.69 1.20
de10 495 0.74 0.74 0.72 0.64 0.45 1.18
de11 495 0.43 0.42 0.30 0.27 0.46 1.20
de1$item.stats %>%
  ggplot(aes(x = row.names(de1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Dependability. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(de1$alpha.drop,
      caption = "Dependability. Subscale statistics when item drop",
      label = 25, digits = 2,
      col.names = alpha_drop_colnames)
Dependability. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
de01 0.73 0.72 0.78 0.21 2.59 0.02 0.07 0.22
de02 0.71 0.70 0.76 0.19 2.32 0.02 0.07 0.22
de03 0.72 0.71 0.77 0.20 2.44 0.02 0.07 0.23
de04 0.82 0.82 0.84 0.31 4.49 0.01 0.02 0.32
de05 0.73 0.72 0.76 0.21 2.59 0.02 0.07 0.22
de06 0.71 0.71 0.77 0.19 2.42 0.02 0.07 0.22
de07 0.73 0.72 0.78 0.20 2.56 0.02 0.07 0.22
de08 0.71 0.70 0.76 0.19 2.39 0.02 0.06 0.22
de09 0.75 0.74 0.78 0.22 2.88 0.02 0.07 0.30
de10 0.70 0.69 0.76 0.19 2.28 0.02 0.06 0.22
de11 0.75 0.75 0.80 0.23 2.93 0.02 0.08 0.32
kable(de1$response.freq,
      caption = "Dependability. Non missing response frequency for each item",
      label = 26, digits = 2)
Dependability. Non missing response frequency for each item
0 1 2 3 4 5 miss
de01 0.05 0.11 0.24 0.43 0.14 0.03 0
de02 0.09 0.17 0.36 0.26 0.10 0.02 0
de03 0.10 0.17 0.35 0.27 0.09 0.03 0
de04 0.07 0.26 0.45 0.14 0.05 0.02 0
de05 0.02 0.03 0.10 0.28 0.34 0.23 0
de06 0.10 0.17 0.32 0.28 0.11 0.03 0
de07 0.02 0.06 0.27 0.42 0.20 0.03 0
de08 0.04 0.10 0.24 0.44 0.15 0.03 0
de09 0.01 0.06 0.13 0.27 0.33 0.20 0
de10 0.10 0.15 0.30 0.34 0.10 0.02 0
de11 0.07 0.20 0.28 0.31 0.12 0.03 0

Understanding

un1 <- psych::alpha(
  taia %>% select(all_of(un_items)),
  cumulative = TRUE,
  title = "Understanding Factor",
  check.keys = FALSE
)
kable(un1$total,
      caption = "Understanding. Subscale statistics", 
      label = 27, digits = 2,
      col.names = total_colnames)
Understanding. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.92 0.92 0.92 0.5 12 0.01 31.24 10.15 0.51
un1$item.stats$mean <- un1$item.stats$mean / 5
kable(un1$item.stats,
      caption = "Understanding. Items statistics",
      label = 28, digits = 2,
      col.names = item_stats_colnames)
Understanding. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
un01 495 0.75 0.75 0.73 0.70 0.59 1.05
un02 495 0.84 0.84 0.84 0.81 0.49 1.14
un03 495 0.59 0.59 0.54 0.51 0.60 1.17
un04 495 0.76 0.76 0.73 0.71 0.52 1.09
un05 495 0.81 0.81 0.80 0.77 0.56 1.10
un06 495 0.57 0.56 0.50 0.48 0.46 1.23
un07 495 0.72 0.72 0.69 0.66 0.43 1.18
un08 495 0.76 0.76 0.75 0.71 0.58 1.16
un09 495 0.73 0.73 0.69 0.67 0.46 1.23
un10 495 0.75 0.75 0.72 0.69 0.45 1.15
un11 495 0.79 0.79 0.77 0.74 0.53 1.20
un12 495 0.75 0.76 0.73 0.70 0.58 1.12
un1$item.stats %>%
  ggplot(aes(x = row.names(un1$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Understanding. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(un1$alpha.drop,
      caption = "Understanding. Subscale statistics when item drop",
      label = 29, digits = 2,
      col.names = alpha_drop_colnames)
Understanding. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
un01 0.91 0.92 0.91 0.50 10.87 0.01 0.01 0.51
un02 0.91 0.91 0.91 0.48 10.26 0.01 0.01 0.50
un03 0.92 0.92 0.92 0.52 12.05 0.01 0.01 0.54
un04 0.91 0.92 0.92 0.50 10.82 0.01 0.01 0.51
un05 0.91 0.91 0.91 0.49 10.46 0.01 0.01 0.50
un06 0.92 0.92 0.92 0.53 12.30 0.01 0.01 0.54
un07 0.92 0.92 0.92 0.50 11.10 0.01 0.01 0.51
un08 0.91 0.92 0.91 0.50 10.80 0.01 0.01 0.51
un09 0.92 0.92 0.92 0.50 11.06 0.01 0.01 0.51
un10 0.91 0.92 0.92 0.50 10.93 0.01 0.01 0.51
un11 0.91 0.91 0.91 0.49 10.62 0.01 0.01 0.50
un12 0.91 0.92 0.92 0.50 10.86 0.01 0.01 0.50
kable(un1$response.freq,
      caption = "Understanding. Non missing response frequency for each item",
      label = 30, digits = 2)
Understanding. Non missing response frequency for each item
0 1 2 3 4 5 miss
un01 0.02 0.07 0.19 0.43 0.24 0.05 0
un02 0.05 0.14 0.29 0.35 0.14 0.03 0
un03 0.03 0.08 0.16 0.36 0.29 0.07 0
un04 0.03 0.13 0.24 0.40 0.17 0.02 0
un05 0.04 0.08 0.19 0.44 0.21 0.04 0
un06 0.06 0.24 0.28 0.25 0.14 0.04 0
un07 0.09 0.21 0.30 0.29 0.09 0.02 0
un08 0.04 0.09 0.18 0.39 0.23 0.06 0
un09 0.08 0.18 0.25 0.30 0.17 0.01 0
un10 0.06 0.20 0.33 0.27 0.12 0.02 0
un11 0.05 0.13 0.23 0.36 0.18 0.05 0
un12 0.03 0.08 0.19 0.41 0.23 0.06 0
omega(taia %>% ungroup() %>% select(all_of(taia_items)),
      nfactors=6, p=.05, poly=FALSE,
      digits=2, title="Omega", sl=TRUE, plot=TRUE, covar=FALSE)
## Loading required namespace: GPArotation

## Omega 
## Call: omegah(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip, 
##     digits = digits, title = title, sl = sl, labels = labels, 
##     plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option, 
##     covar = covar)
## Alpha:                 0.94 
## G.6:                   0.97 
## Omega Hierarchical:    0.6 
## Omega H asymptotic:    0.62 
## Omega Total            0.96 
## 
## Schmid Leiman Factor loadings greater than  0.2 
##           g   F1*   F2*   F3*   F4*   F5*   F6*   h2   u2   p2
## pr01   0.57  0.34        0.26                   0.57 0.43 0.58
## pr02   0.45                                     0.32 0.68 0.65
## pr03   0.20                                0.54 0.39 0.61 0.10
## pr04                                       0.43 0.24 0.76 0.02
## pr05   0.56                          0.45       0.52 0.48 0.60
## pr06   0.43  0.37                               0.35 0.65 0.53
## pr07   0.57  0.24        0.25        0.21       0.50 0.50 0.66
## pr08   0.52  0.38        0.23                   0.49 0.51 0.54
## pr09   0.41  0.29                               0.29 0.71 0.57
## pr10   0.37  0.25                               0.23 0.77 0.58
## co01   0.51              0.51                   0.54 0.46 0.48
## co02   0.44              0.55                   0.49 0.51 0.39
## co03   0.47  0.29                               0.37 0.63 0.60
## co04   0.33  0.44                               0.38 0.62 0.28
## co05   0.44              0.63                   0.60 0.40 0.33
## co06   0.37              0.51                   0.40 0.60 0.34
## co07-        0.29                               0.17 0.83 0.11
## co08                     0.34             -0.37 0.41 0.59 0.02
## co09   0.40              0.60                   0.54 0.46 0.29
## co10   0.38              0.45                   0.40 0.60 0.36
## ut01   0.36  0.67                               0.61 0.39 0.21
## ut02   0.45  0.63                               0.64 0.36 0.31
## ut03   0.22  0.32                          0.52 0.54 0.46 0.09
## ut04   0.27  0.39                               0.24 0.76 0.31
## ut05   0.41  0.44                               0.37 0.63 0.45
## ut06   0.46  0.60                               0.56 0.44 0.38
## ut07   0.34  0.46                               0.34 0.66 0.35
## ut08   0.40  0.47                               0.40 0.60 0.39
## ut09   0.42  0.46                               0.39 0.61 0.44
## ut10                                       0.24 0.09 0.91 0.03
## ut11   0.54  0.21                    0.39       0.48 0.52 0.61
## ut12   0.46  0.47                               0.45 0.55 0.47
## fa01   0.44                    0.61             0.60 0.40 0.33
## fa02                           0.67             0.54 0.46 0.00
## fa03                                      -0.37 0.31 0.69 0.12
## fa04   0.35              0.32        0.21       0.40 0.60 0.32
## fa05   0.47                    0.60             0.62 0.38 0.36
## fa06   0.58              0.30                   0.52 0.48 0.65
## fa07   0.23                          0.20  0.47 0.36 0.64 0.14
## fa08                           0.61             0.49 0.51 0.00
## fa09                           0.64        0.23 0.55 0.45 0.02
## fa10   0.24                    0.63             0.48 0.52 0.12
## de01   0.43                                     0.29 0.71 0.63
## de02   0.57              0.23        0.30       0.49 0.51 0.67
## de03   0.50                          0.28       0.38 0.62 0.65
## de04-  0.31  0.39                               0.27 0.73 0.37
## de05   0.38  0.41                          0.29 0.45 0.55 0.32
## de06   0.58                          0.47       0.58 0.42 0.59
## de07   0.49  0.34                               0.40 0.60 0.59
## de08   0.54  0.23                    0.25       0.43 0.57 0.68
## de09   0.22                                0.59 0.43 0.57 0.12
## de10   0.60                          0.40       0.56 0.44 0.64
## de11   0.22                          0.24  0.32 0.27 0.73 0.18
## un01   0.25        0.72                         0.63 0.37 0.10
## un02   0.28        0.79                         0.70 0.30 0.11
## un03               0.43       -0.26             0.36 0.64 0.10
## un04   0.25        0.68                         0.53 0.47 0.12
## un05   0.28        0.77                         0.67 0.33 0.11
## un06        -0.29  0.51                    0.32 0.40 0.60 0.02
## un07   0.33        0.59                         0.54 0.46 0.20
## un08   0.24        0.73                         0.60 0.40 0.10
## un09   0.31        0.61                         0.52 0.48 0.18
## un10   0.27        0.65                         0.57 0.43 0.13
## un11   0.24        0.72                         0.60 0.40 0.10
## un12   0.26        0.68                         0.57 0.43 0.12
## 
## With eigenvalues of:
##   g F1* F2* F3* F4* F5* F6* 
## 9.4 4.6 5.6 2.8 2.7 1.6 2.3 
## 
## general/max  1.68   max/min =   3.6
## mean percent general =  0.32    with sd =  0.22 and cv of  0.68 
## Explained Common Variance of the general factor =  0.32 
## 
## The degrees of freedom are 1705  and the fit is  8.03 
## The number of observations was  495  with Chi Square =  3753.55  with prob <  2.4e-155
## The root mean square of the residuals is  0.04 
## The df corrected root mean square of the residuals is  0.04
## RMSEA index =  0.049  and the 10 % confidence intervals are  0.047 0.051
## BIC =  -6825.22
## 
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 2015  and the fit is  22.88 
## The number of observations was  495  with Chi Square =  10774.78  with prob <  0
## The root mean square of the residuals is  0.15 
## The df corrected root mean square of the residuals is  0.15 
## 
## RMSEA index =  0.094  and the 10 % confidence intervals are  0.092 0.096
## BIC =  -1727.41 
## 
## Measures of factor score adequacy             
##                                                  g  F1*  F2*  F3*  F4*  F5*
## Correlation of scores with factors            0.81 0.89 0.97 0.86 0.94 0.71
## Multiple R square of scores with factors      0.66 0.79 0.94 0.74 0.88 0.50
## Minimum correlation of factor score estimates 0.32 0.59 0.88 0.47 0.76 0.00
##                                                F6*
## Correlation of scores with factors            0.91
## Multiple R square of scores with factors      0.83
## Minimum correlation of factor score estimates 0.66
## 
##  Total, General and Subset omega for each subset
##                                                  g  F1*  F2*  F3*  F4*  F5*
## Omega total for total scores and subscales    0.96 0.87 0.91 0.86 0.83 0.81
## Omega general for total scores and subscales  0.60 0.43 0.11 0.45 0.09 0.57
## Omega group for total scores and subscales    0.21 0.44 0.79 0.41 0.74 0.24
##                                                F6*
## Omega total for total scores and subscales    0.51
## Omega general for total scores and subscales  0.14
## Omega group for total scores and subscales    0.37
splitHalf(taia %>% ungroup() %>% select(all_of(taia_items)),
          raw=F, brute=F, n.sample=100, covar=F,
          check.keys=F, key=NULL, use="pairwise")
## Split half reliabilities  
## Call: splitHalf(r = taia %>% ungroup() %>% select(all_of(taia_items)), 
##     raw = F, brute = F, n.sample = 100, covar = F, check.keys = F, 
##     key = NULL, use = "pairwise")
## 
## Maximum split half reliability (lambda 4) =  0.96
## Guttman lambda 6                          =  0.96
## Average split half reliability            =  0.93
## Guttman lambda 3 (alpha)                  =  0.93
## Guttman lambda 2                          =  0.94
## Minimum split half reliability  (beta)    =  0.86
## Average interitem r =  0.17  with median =  0.18
guttman(taia %>% ungroup() %>% select(all_of(taia_items)))
## Warning: Guttman has been deprecated. The use of the splitHalf function is
## recommended
## Warning in splitHalf(r): Some items were negatively correlated with total scale
## and were automatically reversed.
## Call: guttman(r = taia %>% ungroup() %>% select(all_of(taia_items)))
## 
## Alternative estimates of reliability
## 
## Guttman bounds 
## L1 =  0.92 
## L2 =  0.94 
## L3 (alpha) =  0.93 
## L4 (max) =  0.97 
## L5 =  0.92 
## L6 (smc) =  0.96 
## TenBerge bounds 
## mu0 =  0.93 mu1 =  0.94 mu2 =  0.94 mu3 =  0.94 
## 
## alpha of first PC =  0.95 
## estimated greatest lower bound based upon communalities=  0.97 
## 
## beta found by splitHalf  =  0.85
glb.fa(taia %>% ungroup() %>% select(all_of(taia_items)))
## $glb
## [1] 0.965817
## 
## $communality
##      pr01      pr02      pr03      pr04      pr05      pr06      pr07      pr08 
## 0.7253391 0.5393523 0.4690491 0.6292470 0.7830601 0.6280428 0.5758103 0.6112839 
##      pr09      pr10      co01      co02      co03      co04      co05      co06 
## 0.5896570 0.3330770 0.5758243 0.6305638 0.4895706 0.4890165 0.7521395 0.5726406 
##      co07      co08      co09      co10      ut01      ut02      ut03      ut04 
## 0.4356987 0.4665793 0.6337356 0.4811587 0.7718201 0.7277348 0.6422830 0.3722353 
##      ut05      ut06      ut07      ut08      ut09      ut10      ut11      ut12 
## 0.5234489 0.7171434 0.5757501 0.5792722 0.7253062 0.3644927 0.6451266 0.5389414 
##      fa01      fa02      fa03      fa04      fa05      fa06      fa07      fa08 
## 0.6943597 0.5928412 0.4376811 0.5197275 0.7565165 0.5844505 0.4786126 0.6061162 
##      fa09      fa10      de01      de02      de03      de04      de05      de06 
## 0.6945327 0.4919291 0.4216417 0.5711187 0.5654506 0.4521109 0.7942688 0.7264322 
##      de07      de08      de09      de10      de11      un01      un02      un03 
## 0.5278337 0.5885239 0.6875419 0.6514868 0.3425354 0.6718202 0.7379031 0.4402195 
##      un04      un05      un06      un07      un08      un09      un10      un11 
## 0.6398019 0.6914535 0.4729219 0.5759967 0.6904648 0.5762576 0.6507091 0.6870705 
##      un12 
## 0.6276157 
## 
## $numf
## [1] 19
## 
## $Call
## glb.fa(r = taia %>% ungroup() %>% select(all_of(taia_items)))

Items exclusion

First step

Excluded items: co07, ut10, de04

Reason: negative discrimination

Stems:

  • co07 Я могу сказать, что система работает корректно, только протестировав её (R)
  • ut10 Мне кажется, при оформлении услуг через интернет можно справиться и без цифровых помощников (R)
  • de04 Я могу доверять интеллектуальной системе, если я точно понимаю, какие опасности исходят от неё (R)
co_items_old <- co_items
co_items[-7] -> co_items
ut_items_old <- ut_items
ut_items[-10] -> ut_items
de_items_old <- de_items
de_items[-4] -> de_items

Subscales after first step of exclusion

Consistency

co2 <- psych::alpha(
  taia %>% select(all_of(co_items)),
  cumulative = TRUE,
  title = "Consistency Factor",
  check.keys = FALSE
)
kable(co2$total,
      caption = "Consistency. Subscale statistics", 
      label = 11, digits = 2,
      col.names = total_colnames)
Consistency. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.83 0.82 0.83 0.34 4.7 0.01 22.44 6.24 0.36
co2$item.stats$mean <- co2$item.stats$mean / 5
kable(co2$item.stats,
      caption = "Consistency. Items statistics",
      label = 12, digits = 2,
      col.names = item_stats_colnames)
Consistency. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
co01 495 0.74 0.74 0.71 0.65 0.50 1.08
co02 495 0.72 0.72 0.67 0.62 0.50 1.04
co03 495 0.56 0.57 0.48 0.43 0.57 1.02
co04 495 0.44 0.43 0.33 0.28 0.69 1.09
co05 495 0.79 0.78 0.78 0.70 0.44 1.11
co06 495 0.68 0.67 0.62 0.56 0.50 1.11
co08 495 0.44 0.44 0.34 0.29 0.38 1.04
co09 495 0.76 0.76 0.75 0.67 0.41 1.07
co10 495 0.68 0.68 0.62 0.57 0.49 1.10
co2$item.stats %>%
  ggplot(aes(x = row.names(co2$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Consistency. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(co2$alpha.drop,
      caption = "Consistency. Subscale statistics when item drop",
      label = 13, digits = 2,
      col.names = alpha_drop_colnames)
Consistency. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
co01 0.79 0.79 0.80 0.32 3.81 0.01 0.03 0.34
co02 0.80 0.80 0.81 0.33 3.89 0.01 0.03 0.35
co03 0.82 0.82 0.82 0.36 4.49 0.01 0.03 0.41
co04 0.84 0.83 0.83 0.39 5.04 0.01 0.02 0.41
co05 0.79 0.79 0.79 0.31 3.66 0.01 0.02 0.33
co06 0.80 0.80 0.81 0.34 4.06 0.01 0.03 0.35
co08 0.83 0.83 0.83 0.39 5.01 0.01 0.02 0.40
co09 0.79 0.79 0.80 0.32 3.74 0.01 0.02 0.34
co10 0.80 0.80 0.81 0.34 4.04 0.01 0.03 0.35
kable(co2$response.freq,
      caption = "Consistency. Non missing response frequency for each item",
      label = 14, digits = 2)
Consistency. Non missing response frequency for each item
0 1 2 3 4 5 miss
co01 0.05 0.11 0.31 0.39 0.11 0.03 0
co02 0.03 0.12 0.32 0.38 0.13 0.02 0
co03 0.02 0.07 0.22 0.44 0.21 0.04 0
co04 0.01 0.04 0.10 0.35 0.32 0.18 0
co05 0.06 0.19 0.37 0.27 0.09 0.02 0
co06 0.04 0.14 0.28 0.38 0.13 0.03 0
co08 0.08 0.27 0.42 0.16 0.06 0.01 0
co09 0.06 0.24 0.40 0.22 0.06 0.02 0
co10 0.04 0.14 0.33 0.34 0.11 0.03 0

Utility

ut2 <- psych::alpha(
  taia %>% select(all_of(ut_items)),
  cumulative = TRUE,
  title = "Utility Factor",
  check.keys = FALSE
)
kable(ut2$total,
      caption = "Utility. Subscale statistics", 
      label = 15, digits = 2,
      col.names = total_colnames)
Utility. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.88 0.88 0.88 0.4 7.4 0.01 35.92 8.32 0.41
ut2$item.stats$mean <- ut2$item.stats$mean / 5
kable(ut2$item.stats,
      caption = "Utility. Items statistics",
      label = 16, digits = 2,
      col.names = item_stats_colnames)
Utility. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
ut01 495 0.79 0.79 0.79 0.73 0.76 1.05
ut02 495 0.83 0.84 0.84 0.79 0.70 1.05
ut03 495 0.55 0.56 0.49 0.45 0.71 1.11
ut04 495 0.53 0.53 0.46 0.42 0.62 1.11
ut05 495 0.69 0.68 0.64 0.60 0.61 1.21
ut06 495 0.77 0.77 0.75 0.71 0.65 1.10
ut07 495 0.62 0.62 0.57 0.52 0.64 1.13
ut08 495 0.66 0.67 0.62 0.58 0.69 1.05
ut09 495 0.70 0.70 0.66 0.62 0.64 1.17
ut11 495 0.57 0.56 0.49 0.46 0.53 1.23
ut12 495 0.72 0.72 0.68 0.65 0.63 1.15
ut2$item.stats %>%
  ggplot(aes(x = row.names(ut2$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Utility. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(ut2$alpha.drop,
      caption = "Utility. Subscale statistics when item drop",
      label = 17, digits = 2,
      col.names = alpha_drop_colnames)
Utility. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
ut01 0.86 0.86 0.86 0.38 6.21 0.01 0.01 0.40
ut02 0.86 0.86 0.86 0.38 6.01 0.01 0.01 0.37
ut03 0.88 0.88 0.88 0.42 7.30 0.01 0.01 0.43
ut04 0.88 0.88 0.88 0.43 7.41 0.01 0.01 0.43
ut05 0.87 0.87 0.87 0.40 6.69 0.01 0.01 0.41
ut06 0.86 0.86 0.87 0.39 6.30 0.01 0.01 0.41
ut07 0.87 0.87 0.87 0.41 6.99 0.01 0.01 0.42
ut08 0.87 0.87 0.87 0.40 6.77 0.01 0.01 0.41
ut09 0.87 0.87 0.87 0.40 6.64 0.01 0.02 0.41
ut11 0.88 0.88 0.88 0.42 7.27 0.01 0.01 0.44
ut12 0.86 0.87 0.87 0.39 6.52 0.01 0.02 0.41
kable(ut2$response.freq,
      caption = "Utility. Non missing response frequency for each item",
      label = 18, digits = 2)
Utility. Non missing response frequency for each item
0 1 2 3 4 5 miss
ut01 0.01 0.01 0.06 0.29 0.34 0.28 0
ut02 0.01 0.02 0.09 0.38 0.30 0.20 0
ut03 0.01 0.04 0.09 0.33 0.31 0.22 0
ut04 0.02 0.08 0.15 0.40 0.27 0.09 0
ut05 0.03 0.06 0.20 0.35 0.23 0.12 0
ut06 0.03 0.03 0.13 0.39 0.30 0.12 0
ut07 0.01 0.05 0.19 0.35 0.26 0.14 0
ut08 0.01 0.03 0.11 0.36 0.34 0.15 0
ut09 0.03 0.05 0.15 0.38 0.25 0.13 0
ut11 0.05 0.12 0.27 0.32 0.18 0.07 0
ut12 0.02 0.07 0.15 0.38 0.26 0.12 0

Dependability

de2 <- psych::alpha(
  taia %>% select(all_of(de_items)),
  cumulative = TRUE,
  title = "Dependability Factor",
  check.keys = FALSE
)
kable(de2$total,
      caption = "Dependability. Subscale statistics", 
      label = 23, digits = 2,
      col.names = total_colnames)
Dependability. Subscale statistics
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Scale Mean Total Score SD Median interitem correlation
0.82 0.82 0.84 0.31 4.49 0.01 26.19 7.05 0.32
de2$item.stats$mean <- de2$item.stats$mean / 5
kable(de2$item.stats,
      caption = "Dependability. Items statistics",
      label = 24, digits = 2,
      col.names = item_stats_colnames)
Dependability. Items statistics
Num. of Obs. Discrimination Std Cor Cor Overlap Corrected Cor if drop Difficulty SD
de01 495 0.58 0.59 0.53 0.47 0.52 1.10
de02 495 0.72 0.72 0.68 0.62 0.43 1.15
de03 495 0.65 0.65 0.60 0.54 0.43 1.19
de05 495 0.62 0.62 0.59 0.50 0.71 1.16
de06 495 0.67 0.67 0.62 0.56 0.45 1.23
de07 495 0.61 0.62 0.56 0.51 0.56 1.00
de08 495 0.70 0.71 0.67 0.61 0.53 1.06
de09 495 0.46 0.45 0.40 0.31 0.69 1.20
de10 495 0.73 0.73 0.71 0.64 0.45 1.18
de11 495 0.41 0.40 0.28 0.25 0.46 1.20
de2$item.stats %>%
  ggplot(aes(x = row.names(de2$item.stats))) +
  geom_point(aes(y = mean), color = "darkblue", size = 3) +
  geom_point(aes(y = raw.r), color = "darkred", size = 2) +
  geom_hline(yintercept = 0.1, color = "darkblue") +
  geom_hline(yintercept = 0.9, color = "darkblue") +
  geom_hline(yintercept = 0.25, color = "darkred") +
  geom_hline(yintercept = 0, color = "black") +
  labs(x = "Item", y = "Value",
       title = "Dependability. Items characteristics",
       subtitle = "Difficulty (blue) and Dicrimination (red)") +
  theme(plot.title = element_text(hjust = .5),
        plot.subtitle = element_text(hjust = .5))

kable(de2$alpha.drop,
      caption = "Dependability. Subscale statistics when item drop",
      label = 25, digits = 2,
      col.names = alpha_drop_colnames)
Dependability. Subscale statistics when item drop
Alpha Standardized Alpha Guttman’s Lambda 6 Average interitem correlation S/N Alpha SE Var(r) Median interitem correlation
de01 0.80 0.80 0.82 0.31 4.11 0.01 0.02 0.31
de02 0.79 0.79 0.81 0.29 3.72 0.01 0.02 0.29
de03 0.79 0.80 0.82 0.30 3.93 0.01 0.02 0.29
de05 0.80 0.80 0.80 0.31 4.04 0.01 0.02 0.35
de06 0.79 0.80 0.81 0.30 3.88 0.01 0.02 0.31
de07 0.80 0.80 0.82 0.31 4.02 0.01 0.02 0.29
de08 0.79 0.79 0.81 0.29 3.75 0.01 0.02 0.29
de09 0.82 0.82 0.82 0.34 4.60 0.01 0.02 0.35
de10 0.78 0.79 0.80 0.29 3.67 0.01 0.02 0.29
de11 0.83 0.83 0.84 0.35 4.79 0.01 0.02 0.37
kable(de2$response.freq,
      caption = "Dependability. Non missing response frequency for each item",
      label = 26, digits = 2)
Dependability. Non missing response frequency for each item
0 1 2 3 4 5 miss
de01 0.05 0.11 0.24 0.43 0.14 0.03 0
de02 0.09 0.17 0.36 0.26 0.10 0.02 0
de03 0.10 0.17 0.35 0.27 0.09 0.03 0
de05 0.02 0.03 0.10 0.28 0.34 0.23 0
de06 0.10 0.17 0.32 0.28 0.11 0.03 0
de07 0.02 0.06 0.27 0.42 0.20 0.03 0
de08 0.04 0.10 0.24 0.44 0.15 0.03 0
de09 0.01 0.06 0.13 0.27 0.33 0.20 0
de10 0.10 0.15 0.30 0.34 0.10 0.02 0
de11 0.07 0.20 0.28 0.31 0.12 0.03 0

Reliability measures

omega(taia %>% ungroup() %>% select(all_of(taia_items)),
      nfactors=6, p=.05, poly=FALSE,
      digits=2, title="Omega", sl=TRUE, plot=TRUE, covar=FALSE)

## Omega 
## Call: omegah(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip, 
##     digits = digits, title = title, sl = sl, labels = labels, 
##     plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option, 
##     covar = covar)
## Alpha:                 0.94 
## G.6:                   0.97 
## Omega Hierarchical:    0.6 
## Omega H asymptotic:    0.62 
## Omega Total            0.96 
## 
## Schmid Leiman Factor loadings greater than  0.2 
##           g   F1*   F2*   F3*   F4*   F5*   F6*   h2   u2   p2
## pr01   0.57  0.34        0.26                   0.57 0.43 0.58
## pr02   0.45                                     0.32 0.68 0.65
## pr03   0.20                                0.54 0.39 0.61 0.10
## pr04                                       0.43 0.24 0.76 0.02
## pr05   0.56                          0.45       0.52 0.48 0.60
## pr06   0.43  0.37                               0.35 0.65 0.53
## pr07   0.57  0.24        0.25        0.21       0.50 0.50 0.66
## pr08   0.52  0.38        0.23                   0.49 0.51 0.54
## pr09   0.41  0.29                               0.29 0.71 0.57
## pr10   0.37  0.25                               0.23 0.77 0.58
## co01   0.51              0.51                   0.54 0.46 0.48
## co02   0.44              0.55                   0.49 0.51 0.39
## co03   0.47  0.29                               0.37 0.63 0.60
## co04   0.33  0.44                               0.38 0.62 0.28
## co05   0.44              0.63                   0.60 0.40 0.33
## co06   0.37              0.51                   0.40 0.60 0.34
## co07-        0.29                               0.17 0.83 0.11
## co08                     0.34             -0.37 0.41 0.59 0.02
## co09   0.40              0.60                   0.54 0.46 0.29
## co10   0.38              0.45                   0.40 0.60 0.36
## ut01   0.36  0.67                               0.61 0.39 0.21
## ut02   0.45  0.63                               0.64 0.36 0.31
## ut03   0.22  0.32                          0.52 0.54 0.46 0.09
## ut04   0.27  0.39                               0.24 0.76 0.31
## ut05   0.41  0.44                               0.37 0.63 0.45
## ut06   0.46  0.60                               0.56 0.44 0.38
## ut07   0.34  0.46                               0.34 0.66 0.35
## ut08   0.40  0.47                               0.40 0.60 0.39
## ut09   0.42  0.46                               0.39 0.61 0.44
## ut10                                       0.24 0.09 0.91 0.03
## ut11   0.54  0.21                    0.39       0.48 0.52 0.61
## ut12   0.46  0.47                               0.45 0.55 0.47
## fa01   0.44                    0.61             0.60 0.40 0.33
## fa02                           0.67             0.54 0.46 0.00
## fa03                                      -0.37 0.31 0.69 0.12
## fa04   0.35              0.32        0.21       0.40 0.60 0.32
## fa05   0.47                    0.60             0.62 0.38 0.36
## fa06   0.58              0.30                   0.52 0.48 0.65
## fa07   0.23                          0.20  0.47 0.36 0.64 0.14
## fa08                           0.61             0.49 0.51 0.00
## fa09                           0.64        0.23 0.55 0.45 0.02
## fa10   0.24                    0.63             0.48 0.52 0.12
## de01   0.43                                     0.29 0.71 0.63
## de02   0.57              0.23        0.30       0.49 0.51 0.67
## de03   0.50                          0.28       0.38 0.62 0.65
## de04-  0.31  0.39                               0.27 0.73 0.37
## de05   0.38  0.41                          0.29 0.45 0.55 0.32
## de06   0.58                          0.47       0.58 0.42 0.59
## de07   0.49  0.34                               0.40 0.60 0.59
## de08   0.54  0.23                    0.25       0.43 0.57 0.68
## de09   0.22                                0.59 0.43 0.57 0.12
## de10   0.60                          0.40       0.56 0.44 0.64
## de11   0.22                          0.24  0.32 0.27 0.73 0.18
## un01   0.25        0.72                         0.63 0.37 0.10
## un02   0.28        0.79                         0.70 0.30 0.11
## un03               0.43       -0.26             0.36 0.64 0.10
## un04   0.25        0.68                         0.53 0.47 0.12
## un05   0.28        0.77                         0.67 0.33 0.11
## un06        -0.29  0.51                    0.32 0.40 0.60 0.02
## un07   0.33        0.59                         0.54 0.46 0.20
## un08   0.24        0.73                         0.60 0.40 0.10
## un09   0.31        0.61                         0.52 0.48 0.18
## un10   0.27        0.65                         0.57 0.43 0.13
## un11   0.24        0.72                         0.60 0.40 0.10
## un12   0.26        0.68                         0.57 0.43 0.12
## 
## With eigenvalues of:
##   g F1* F2* F3* F4* F5* F6* 
## 9.4 4.6 5.6 2.8 2.7 1.6 2.3 
## 
## general/max  1.68   max/min =   3.6
## mean percent general =  0.32    with sd =  0.22 and cv of  0.68 
## Explained Common Variance of the general factor =  0.32 
## 
## The degrees of freedom are 1705  and the fit is  8.03 
## The number of observations was  495  with Chi Square =  3753.55  with prob <  2.4e-155
## The root mean square of the residuals is  0.04 
## The df corrected root mean square of the residuals is  0.04
## RMSEA index =  0.049  and the 10 % confidence intervals are  0.047 0.051
## BIC =  -6825.22
## 
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 2015  and the fit is  22.88 
## The number of observations was  495  with Chi Square =  10774.78  with prob <  0
## The root mean square of the residuals is  0.15 
## The df corrected root mean square of the residuals is  0.15 
## 
## RMSEA index =  0.094  and the 10 % confidence intervals are  0.092 0.096
## BIC =  -1727.41 
## 
## Measures of factor score adequacy             
##                                                  g  F1*  F2*  F3*  F4*  F5*
## Correlation of scores with factors            0.81 0.89 0.97 0.86 0.94 0.71
## Multiple R square of scores with factors      0.66 0.79 0.94 0.74 0.88 0.50
## Minimum correlation of factor score estimates 0.32 0.59 0.88 0.47 0.76 0.00
##                                                F6*
## Correlation of scores with factors            0.91
## Multiple R square of scores with factors      0.83
## Minimum correlation of factor score estimates 0.66
## 
##  Total, General and Subset omega for each subset
##                                                  g  F1*  F2*  F3*  F4*  F5*
## Omega total for total scores and subscales    0.96 0.87 0.91 0.86 0.83 0.81
## Omega general for total scores and subscales  0.60 0.43 0.11 0.45 0.09 0.57
## Omega group for total scores and subscales    0.21 0.44 0.79 0.41 0.74 0.24
##                                                F6*
## Omega total for total scores and subscales    0.51
## Omega general for total scores and subscales  0.14
## Omega group for total scores and subscales    0.37
splitHalf(taia %>% ungroup() %>% select(all_of(taia_items)),
          raw=F, brute=F, n.sample=100, covar=F,
          check.keys=F, key=NULL, use="pairwise")
## Split half reliabilities  
## Call: splitHalf(r = taia %>% ungroup() %>% select(all_of(taia_items)), 
##     raw = F, brute = F, n.sample = 100, covar = F, check.keys = F, 
##     key = NULL, use = "pairwise")
## 
## Maximum split half reliability (lambda 4) =  0.95
## Guttman lambda 6                          =  0.96
## Average split half reliability            =  0.93
## Guttman lambda 3 (alpha)                  =  0.93
## Guttman lambda 2                          =  0.94
## Minimum split half reliability  (beta)    =  0.87
## Average interitem r =  0.17  with median =  0.18
guttman(taia %>% ungroup() %>% select(all_of(taia_items)))
## Warning: Guttman has been deprecated. The use of the splitHalf function is
## recommended
## Warning in splitHalf(r): Some items were negatively correlated with total scale
## and were automatically reversed.
## Call: guttman(r = taia %>% ungroup() %>% select(all_of(taia_items)))
## 
## Alternative estimates of reliability
## 
## Guttman bounds 
## L1 =  0.92 
## L2 =  0.94 
## L3 (alpha) =  0.93 
## L4 (max) =  0.97 
## L5 =  0.92 
## L6 (smc) =  0.96 
## TenBerge bounds 
## mu0 =  0.93 mu1 =  0.94 mu2 =  0.94 mu3 =  0.94 
## 
## alpha of first PC =  0.95 
## estimated greatest lower bound based upon communalities=  0.97 
## 
## beta found by splitHalf  =  0.85
glb.fa(taia %>% ungroup() %>% select(all_of(taia_items)))
## $glb
## [1] 0.965817
## 
## $communality
##      pr01      pr02      pr03      pr04      pr05      pr06      pr07      pr08 
## 0.7253391 0.5393523 0.4690491 0.6292470 0.7830601 0.6280428 0.5758103 0.6112839 
##      pr09      pr10      co01      co02      co03      co04      co05      co06 
## 0.5896570 0.3330770 0.5758243 0.6305638 0.4895706 0.4890165 0.7521395 0.5726406 
##      co07      co08      co09      co10      ut01      ut02      ut03      ut04 
## 0.4356987 0.4665793 0.6337356 0.4811587 0.7718201 0.7277348 0.6422830 0.3722353 
##      ut05      ut06      ut07      ut08      ut09      ut10      ut11      ut12 
## 0.5234489 0.7171434 0.5757501 0.5792722 0.7253062 0.3644927 0.6451266 0.5389414 
##      fa01      fa02      fa03      fa04      fa05      fa06      fa07      fa08 
## 0.6943597 0.5928412 0.4376811 0.5197275 0.7565165 0.5844505 0.4786126 0.6061162 
##      fa09      fa10      de01      de02      de03      de04      de05      de06 
## 0.6945327 0.4919291 0.4216417 0.5711187 0.5654506 0.4521109 0.7942688 0.7264322 
##      de07      de08      de09      de10      de11      un01      un02      un03 
## 0.5278337 0.5885239 0.6875419 0.6514868 0.3425354 0.6718202 0.7379031 0.4402195 
##      un04      un05      un06      un07      un08      un09      un10      un11 
## 0.6398019 0.6914535 0.4729219 0.5759967 0.6904648 0.5762576 0.6507091 0.6870705 
##      un12 
## 0.6276157 
## 
## $numf
## [1] 19
## 
## $Call
## glb.fa(r = taia %>% ungroup() %>% select(all_of(taia_items)))

Exploratory Factor Analysis

taia_items <- c(
  pr_items, co_items, ut_items, fa_items, de_items, un_items
)

6 factors, varimax rotation

efa_6f_vm <- factanal(taia %>% select(all_of(taia_items)),
                   factors = 6,
                   scores = "regression",
                   rotation = "varimax")
loadings(efa_6f_vm)
## 
## Loadings:
##      Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## pr01  0.489   0.475   0.172           0.287         
## pr02  0.263   0.392   0.219           0.164   0.181 
## pr03  0.219                           0.547         
## pr04         -0.109           0.139   0.437         
## pr05  0.204   0.350   0.139           0.123   0.676 
## pr06  0.475   0.279   0.144                   0.105 
## pr07  0.387   0.525                   0.208   0.134 
## pr08  0.492   0.429   0.125           0.241         
## pr09  0.350   0.347   0.133           0.220         
## pr10  0.328   0.301   0.124           0.108         
## co01  0.243   0.676           0.116                 
## co02  0.169   0.626   0.115                         
## co03  0.416   0.370                   0.159   0.141 
## co04  0.532   0.147   0.121           0.161         
## co05  0.137   0.724                                 
## co06  0.152   0.554          -0.117                 
## co08 -0.118   0.413  -0.115  -0.127  -0.467         
## co09          0.676                  -0.160         
## co10  0.184   0.526   0.206          -0.123         
## ut01  0.810                                         
## ut02  0.806           0.102           0.135   0.125 
## ut03  0.472  -0.102           0.119   0.507         
## ut04  0.461                   0.104           0.132 
## ut05  0.598   0.194                                 
## ut06  0.717   0.164                           0.125 
## ut07  0.550   0.207                                 
## ut08  0.576   0.249                                 
## ut09  0.593   0.174                   0.102   0.128 
## ut11  0.368   0.255   0.158           0.126   0.591 
## ut12  0.604   0.233   0.135           0.142         
## fa01  0.300   0.345           0.628                 
## fa02                 -0.207   0.669   0.148         
## fa03 -0.116   0.385                  -0.318   0.148 
## fa04          0.549           0.103  -0.192   0.177 
## fa05  0.293   0.411           0.622                 
## fa06  0.301   0.573   0.126   0.188   0.182   0.163 
## fa07                          0.196   0.474   0.193 
## fa08                 -0.191   0.602   0.232         
## fa09                 -0.155   0.631   0.310         
## fa10  0.280   0.136           0.599                 
## de01  0.278   0.429   0.162                         
## de02  0.225   0.571   0.129           0.155   0.228 
## de03  0.223   0.475   0.115   0.138           0.214 
## de05  0.508   0.173   0.137           0.385         
## de06  0.218   0.352   0.184   0.171           0.666 
## de07  0.439   0.301   0.220                   0.182 
## de08  0.345   0.412   0.193   0.107   0.185   0.205 
## de09  0.259                           0.592         
## de10  0.287   0.512           0.177           0.351 
## de11                          0.181   0.332   0.255 
## un01  0.287           0.731                         
## un02          0.138   0.815                         
## un03  0.207           0.502  -0.247                 
## un04          0.113   0.711                         
## un05  0.191           0.791                         
## un06 -0.131           0.518           0.189         
## un07          0.286   0.648          -0.139   0.128 
## un08  0.182           0.746                         
## un09          0.162   0.662                   0.197 
## un10          0.261   0.690                         
## un11                  0.763                         
## un12  0.236           0.713                         
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## SS loadings      7.605   7.077   6.534   2.832   2.786   2.029
## Proportion Var   0.123   0.114   0.105   0.046   0.045   0.033
## Cumulative Var   0.123   0.237   0.342   0.388   0.433   0.466
kable(sort(efa_6f_vm$uniquenesses, decreasing = TRUE), col.names = "U")
U
de11 0.7817421
pr04 0.7700534
pr10 0.7616189
ut04 0.7559106
fa03 0.7134353
de01 0.7002496
fa07 0.6907293
pr09 0.6888357
un06 0.6751271
pr02 0.6694849
pr06 0.6576002
ut07 0.6510578
co04 0.6481729
co06 0.6474121
de03 0.6464066
un03 0.6402866
pr03 0.6384384
co03 0.6327467
co10 0.6282188
de07 0.6246089
fa04 0.6137315
ut08 0.5910384
ut05 0.5868681
ut09 0.5865585
de08 0.5858475
de09 0.5766570
co08 0.5671255
co02 0.5579891
de05 0.5437340
fa10 0.5420869
ut12 0.5382611
fa08 0.5284220
de02 0.5246474
co09 0.5063667
pr07 0.4996945
pr08 0.4983024
ut03 0.4937529
de10 0.4934491
un09 0.4875879
fa09 0.4737183
fa02 0.4731288
fa06 0.4702934
un04 0.4642368
co01 0.4635405
un07 0.4574466
co05 0.4479825
ut06 0.4362455
un10 0.4358851
un12 0.4312571
pr01 0.4144342
ut11 0.4071750
un08 0.4066783
un11 0.3931924
fa01 0.3816574
un01 0.3730108
fa05 0.3486393
pr05 0.3357658
ut01 0.3321338
un05 0.3254634
de06 0.3122163
un02 0.3085120
ut02 0.3006345

6 factors, promax rotation

efa_6f_pm <- factanal(taia %>% select(all_of(taia_items)),
                   factors = 6,
                   scores = "regression",
                   rotation = "promax")
loadings(efa_6f_pm)
## 
## Loadings:
##      Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## pr01  0.461           0.225   0.283                 
## pr02  0.338   0.110           0.148           0.136 
## pr03         -0.110           0.614                 
## pr04 -0.141                   0.484                 
## pr05                                          0.790 
## pr06  0.174           0.410                         
## pr07  0.527           0.131   0.192                 
## pr08  0.422           0.278   0.238                 
## pr09  0.361           0.146   0.227                 
## pr10  0.263           0.204          -0.122         
## co01  0.809                           0.102  -0.145 
## co02  0.765                                  -0.137 
## co03  0.303           0.264   0.114                 
## co04                  0.493   0.121          -0.132 
## co05  0.902  -0.102  -0.117                  -0.109 
## co06  0.668                          -0.154         
## co08  0.542  -0.180          -0.501  -0.100         
## co09  0.817  -0.113  -0.123  -0.169                 
## co10  0.598   0.115          -0.135                 
## ut01 -0.249           0.974                         
## ut02 -0.231           0.910                   0.113 
## ut03 -0.213           0.385   0.515                 
## ut04 -0.198           0.552                   0.146 
## ut05                  0.658  -0.124                 
## ut06                  0.789                   0.108 
## ut07  0.128           0.593                         
## ut08  0.186           0.543                  -0.108 
## ut09                  0.608                   0.110 
## ut11                  0.291                   0.694 
## ut12  0.106           0.559                         
## fa01  0.277   0.125   0.171           0.650         
## fa02                 -0.129           0.695         
## fa03  0.418          -0.154  -0.379           0.158 
## fa04  0.609          -0.225  -0.241           0.146 
## fa05  0.367   0.105   0.156  -0.119   0.648         
## fa06  0.580                   0.149   0.131         
## fa07                 -0.218   0.508   0.109   0.173 
## fa08                 -0.179   0.165   0.604         
## fa09                 -0.187   0.254   0.627         
## fa10                  0.281  -0.127   0.648  -0.119 
## de01  0.460                                         
## de02  0.569                   0.135           0.166 
## de03  0.430                                   0.173 
## de05  0.114           0.340   0.407  -0.107         
## de06                                          0.770 
## de07  0.160   0.109   0.337                   0.156 
## de08  0.329           0.129   0.141           0.153 
## de09                          0.692  -0.101         
## de10  0.397           0.106           0.103   0.339 
## de11         -0.106  -0.103   0.320   0.101   0.273 
## un01 -0.148   0.804   0.225           0.123  -0.141 
## un02          0.857  -0.105                         
## un03          0.451   0.145          -0.247         
## un04          0.734                                 
## un05          0.844                                 
## un06          0.556  -0.347   0.256                 
## un07  0.192   0.641  -0.115  -0.172           0.113 
## un08 -0.114   0.817                   0.113         
## un09          0.646  -0.101                   0.212 
## un10  0.219   0.698  -0.212                         
## un11          0.803          -0.103                 
## un12 -0.180   0.740   0.166                         
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## SS loadings      7.535   6.547   6.389   3.041   2.823   2.419
## Proportion Var   0.122   0.106   0.103   0.049   0.046   0.039
## Cumulative Var   0.122   0.227   0.330   0.379   0.425   0.464
kable(
  sort(efa_6f_pm$uniquenesses, decreasing = TRUE),
  col.names = "U")
U
de11 0.7817421
pr04 0.7700534
pr10 0.7616189
ut04 0.7559106
fa03 0.7134353
de01 0.7002496
fa07 0.6907293
pr09 0.6888357
un06 0.6751271
pr02 0.6694849
pr06 0.6576002
ut07 0.6510578
co04 0.6481729
co06 0.6474121
de03 0.6464066
un03 0.6402866
pr03 0.6384384
co03 0.6327467
co10 0.6282188
de07 0.6246089
fa04 0.6137315
ut08 0.5910384
ut05 0.5868681
ut09 0.5865585
de08 0.5858475
de09 0.5766570
co08 0.5671255
co02 0.5579891
de05 0.5437340
fa10 0.5420869
ut12 0.5382611
fa08 0.5284220
de02 0.5246474
co09 0.5063667
pr07 0.4996945
pr08 0.4983024
ut03 0.4937529
de10 0.4934491
un09 0.4875879
fa09 0.4737183
fa02 0.4731288
fa06 0.4702934
un04 0.4642368
co01 0.4635405
un07 0.4574466
co05 0.4479825
ut06 0.4362455
un10 0.4358851
un12 0.4312571
pr01 0.4144342
ut11 0.4071750
un08 0.4066783
un11 0.3931924
fa01 0.3816574
un01 0.3730108
fa05 0.3486393
pr05 0.3357658
ut01 0.3321338
un05 0.3254634
de06 0.3122163
un02 0.3085120
ut02 0.3006345

5 factors, varimax rotation

efa_5f_vm <- factanal(taia %>% select(all_of(taia_items)),
                   factors = 5,
                   scores = "regression",
                   rotation = "varimax")
loadings(efa_5f_vm)
## 
## Loadings:
##      Factor1 Factor2 Factor3 Factor4 Factor5
## pr01  0.576   0.372   0.170   0.212         
## pr02  0.319   0.359   0.221   0.205         
## pr03  0.306  -0.108           0.412   0.121 
## pr04  0.131  -0.197           0.340   0.154 
## pr05  0.211   0.453   0.156   0.482         
## pr06  0.501   0.249   0.142   0.100         
## pr07  0.456   0.465           0.232         
## pr08  0.567   0.334   0.123   0.160         
## pr09  0.424   0.257   0.129   0.129         
## pr10  0.369   0.262   0.124   0.104         
## co01  0.303   0.625                   0.130 
## co02  0.235   0.573   0.114           0.112 
## co03  0.462   0.329           0.176         
## co04  0.573           0.115                 
## co05  0.197   0.690                         
## co06  0.207   0.520                         
## co08 -0.157   0.505  -0.112  -0.326  -0.146 
## co09  0.121   0.681          -0.100         
## co10  0.219   0.513   0.206  -0.125         
## ut01  0.788                                 
## ut02  0.792           0.100   0.136         
## ut03  0.531  -0.225           0.358   0.140 
## ut04  0.437                   0.115         
## ut05  0.586   0.191                         
## ut06  0.713   0.148                         
## ut07  0.559   0.171                         
## ut08  0.612   0.179                         
## ut09  0.601   0.152           0.128         
## ut11  0.362   0.341   0.171   0.431         
## ut12  0.632   0.179   0.131   0.115         
## fa01  0.317   0.338           0.123   0.618 
## fa02                 -0.206   0.202   0.659 
## fa03 -0.148   0.484          -0.103         
## fa04          0.616                         
## fa05  0.305   0.412                   0.604 
## fa06  0.366   0.528   0.127   0.241   0.179 
## fa07                          0.512   0.182 
## fa08                 -0.190   0.284   0.591 
## fa09                 -0.155   0.321   0.632 
## fa10  0.278   0.126                   0.611 
## de01  0.320   0.386   0.159                 
## de02  0.282   0.553   0.132   0.281         
## de03  0.246   0.493   0.117   0.176   0.105 
## de05  0.583           0.133   0.230         
## de06  0.219   0.462   0.197   0.470         
## de07  0.462   0.290   0.220   0.182         
## de08  0.392   0.386   0.195   0.273         
## de09  0.367                   0.374         
## de10  0.300   0.558           0.303   0.121 
## de11                          0.445   0.153 
## un01  0.301           0.727                 
## un02          0.124   0.815                 
## un03  0.221           0.501          -0.243 
## un04  0.107   0.116   0.712                 
## un05  0.219           0.787                 
## un06                  0.519   0.148         
## un07          0.328   0.651                 
## un08  0.195           0.744                 
## un09          0.198   0.667   0.124  -0.110 
## un10          0.272   0.692          -0.101 
## un11          0.107   0.764                 
## un12  0.242           0.712                 
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5
## SS loadings      8.695   6.882   6.542   2.836   2.744
## Proportion Var   0.140   0.111   0.106   0.046   0.044
## Cumulative Var   0.140   0.251   0.357   0.403   0.447
kable(
  sort(efa_5f_vm$uniquenesses, decreasing = TRUE),
  col.names = "U"
)
U
pr04 0.8036037
ut04 0.7875168
de11 0.7660851
pr10 0.7648954
fa03 0.7322846
pr09 0.7157810
de09 0.7138430
de01 0.7115636
pr03 0.7071547
un06 0.6984492
fa07 0.6934404
pr02 0.6780781
co06 0.6691958
pr06 0.6557484
ut07 0.6500545
co04 0.6435044
de03 0.6411034
un03 0.6404520
co03 0.6336224
co10 0.6291329
de07 0.6207641
ut05 0.6108805
fa04 0.6096628
ut09 0.5950296
co02 0.5895055
ut08 0.5880908
de05 0.5859234
co08 0.5800904
de08 0.5776240
ut12 0.5381209
ut11 0.5378917
fa10 0.5312032
fa08 0.5256412
pr08 0.5255447
ut03 0.5181711
de02 0.5158859
co09 0.5114014
pr07 0.5096638
co01 0.4937745
pr05 0.4926627
de10 0.4869821
un09 0.4861097
fa06 0.4806029
co05 0.4747549
fa09 0.4734086
fa02 0.4713133
de06 0.4691654
un04 0.4646410
un07 0.4595727
ut06 0.4594009
pr01 0.4496805
un10 0.4361787
un12 0.4325425
un08 0.4008023
un11 0.3971241
fa01 0.3854741
ut01 0.3691461
un01 0.3671937
fa05 0.3613714
ut02 0.3407660
un05 0.3303704
un02 0.3106689

5 factors, promax rotation

efa_5f_pm <- factanal(taia %>% select(all_of(taia_items)),
                   factors = 5,
                   scores = "regression",
                   rotation = "promax")
loadings(efa_5f_pm)
## 
## Loadings:
##      Factor1 Factor2 Factor3 Factor4 Factor5
## pr01  0.446   0.279           0.163         
## pr02  0.143   0.296   0.114   0.211         
## pr03  0.233  -0.214  -0.117   0.424         
## pr04         -0.293           0.354   0.107 
## pr05 -0.115   0.392           0.579         
## pr06  0.456   0.170                         
## pr07  0.281   0.412           0.218         
## pr08  0.480   0.250           0.106         
## pr09  0.342   0.189                         
## pr10  0.300   0.206                  -0.112 
## co01  0.146   0.650                   0.122 
## co02          0.599                   0.111 
## co03  0.354   0.265           0.139         
## co04  0.624                                 
## co05          0.759          -0.112         
## co06          0.545                  -0.122 
## co08 -0.181   0.655  -0.178  -0.313  -0.109 
## co09          0.763  -0.105  -0.100         
## co10  0.114   0.531   0.122  -0.157         
## ut01  0.932  -0.173          -0.161         
## ut02  0.859  -0.129                         
## ut03  0.556  -0.375           0.303         
## ut04  0.452                                 
## ut05  0.610   0.111                         
## ut06  0.757                                 
## ut07  0.631   0.114          -0.191         
## ut08  0.655                  -0.102         
## ut09  0.605                                 
## ut11  0.121   0.247           0.486         
## ut12  0.625                                 
## fa01  0.152   0.310   0.125           0.634 
## fa02 -0.203                   0.143   0.681 
## fa03 -0.291   0.581                         
## fa04 -0.281   0.695                         
## fa05  0.129   0.400                   0.620 
## fa06  0.134   0.490           0.229   0.130 
## fa07 -0.104                   0.583   0.102 
## fa08 -0.210                   0.254   0.592 
## fa09 -0.158                   0.280   0.627 
## fa10  0.247   0.110          -0.175   0.648 
## de01  0.200   0.356                         
## de02          0.524           0.319         
## de03          0.478           0.183         
## de05  0.562                   0.179         
## de06 -0.118   0.396           0.550         
## de07  0.346   0.199   0.104   0.156         
## de08  0.192   0.310           0.272         
## de09  0.305  -0.213           0.381         
## de10          0.534           0.332         
## de11                 -0.110   0.509         
## un01  0.258  -0.197   0.810  -0.169   0.132 
## un02                  0.857                 
## un03  0.185           0.450          -0.246 
## un04                  0.739                 
## un05  0.103  -0.121   0.847                 
## un06 -0.250  -0.119   0.556   0.200         
## un07 -0.175   0.266   0.641                 
## un08  0.101  -0.128   0.827  -0.111   0.126 
## un09 -0.166           0.647   0.170         
## un10 -0.202   0.204   0.699                 
## un11                  0.805                 
## un12  0.151  -0.155   0.746                 
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5
## SS loadings      7.635   6.936   6.600   3.174   2.713
## Proportion Var   0.123   0.112   0.106   0.051   0.044
## Cumulative Var   0.123   0.235   0.341   0.393   0.436
kable(
  sort(efa_5f_pm$uniquenesses, decreasing = TRUE),
  col.names = "U"
)
U
pr04 0.8036037
ut04 0.7875168
de11 0.7660851
pr10 0.7648954
fa03 0.7322846
pr09 0.7157810
de09 0.7138430
de01 0.7115636
pr03 0.7071547
un06 0.6984492
fa07 0.6934404
pr02 0.6780781
co06 0.6691958
pr06 0.6557484
ut07 0.6500545
co04 0.6435044
de03 0.6411034
un03 0.6404520
co03 0.6336224
co10 0.6291329
de07 0.6207641
ut05 0.6108805
fa04 0.6096628
ut09 0.5950296
co02 0.5895055
ut08 0.5880908
de05 0.5859234
co08 0.5800904
de08 0.5776240
ut12 0.5381209
ut11 0.5378917
fa10 0.5312032
fa08 0.5256412
pr08 0.5255447
ut03 0.5181711
de02 0.5158859
co09 0.5114014
pr07 0.5096638
co01 0.4937745
pr05 0.4926627
de10 0.4869821
un09 0.4861097
fa06 0.4806029
co05 0.4747549
fa09 0.4734086
fa02 0.4713133
de06 0.4691654
un04 0.4646410
un07 0.4595727
ut06 0.4594009
pr01 0.4496805
un10 0.4361787
un12 0.4325425
un08 0.4008023
un11 0.3971241
fa01 0.3854741
ut01 0.3691461
un01 0.3671937
fa05 0.3613714
ut02 0.3407660
un05 0.3303704
un02 0.3106689

Confirmatory Factor Analysis

Basic model

Model:

mdl1 <- "
PR =~ pr01 + pr02 + pr03 + pr04 + pr05 + pr06 + pr07 + pr08 + pr09 + pr10
CO =~ co01 + co02 + co03 + co04 + co05 + co06 + co08 + co09 + co10
UT =~ ut01 + ut02 + ut03 + ut04 + ut05 + ut06 + ut07 + ut08 + ut09 + ut11 + ut12
FA =~ fa01 + fa02 + fa03 + fa04 + fa05 + fa06 + fa07 + fa08 + fa09 + fa10
DE =~ de01 + de02 + de03 + de05 + de06 + de07 + de08 + de09 + de10 + de11
UN =~ un01 + un02 + un03 + un04 + un05 + un06 + un07 + un08 + un09 + un10 + un11 + un12
"

CFA model fitting:

model1 <- cfa(mdl1, taia %>% select(all_of(taia_items)))
summary(model1)
## lavaan 0.6-8 ended normally after 62 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                       139
##                                                       
##   Number of observations                           495
##                                                       
## Model Test User Model:
##                                                       
##   Test statistic                              6326.223
##   Degrees of freedom                              1814
##   P-value (Chi-square)                           0.000
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   PR =~                                               
##     pr01              1.000                           
##     pr02              0.727    0.055   13.199    0.000
##     pr03              0.386    0.060    6.384    0.000
##     pr04              0.153    0.063    2.431    0.015
##     pr05              0.870    0.068   12.721    0.000
##     pr06              0.808    0.061   13.285    0.000
##     pr07              1.040    0.061   17.095    0.000
##     pr08              0.847    0.050   17.029    0.000
##     pr09              0.714    0.054   13.167    0.000
##     pr10              0.666    0.060   11.105    0.000
##   CO =~                                               
##     co01              1.000                           
##     co02              0.896    0.061   14.596    0.000
##     co03              0.646    0.061   10.618    0.000
##     co04              0.459    0.065    7.065    0.000
##     co05              1.090    0.065   16.652    0.000
##     co06              0.856    0.066   13.052    0.000
##     co08              0.438    0.062    7.047    0.000
##     co09              0.978    0.063   15.527    0.000
##     co10              0.831    0.065   12.804    0.000
##   UT =~                                               
##     ut01              1.000                           
##     ut02              1.083    0.055   19.815    0.000
##     ut03              0.682    0.062   11.048    0.000
##     ut04              0.636    0.062   10.244    0.000
##     ut05              0.965    0.066   14.724    0.000
##     ut06              1.008    0.058   17.348    0.000
##     ut07              0.790    0.062   12.676    0.000
##     ut08              0.807    0.057   14.082    0.000
##     ut09              0.945    0.063   14.930    0.000
##     ut11              0.789    0.068   11.527    0.000
##     ut12              0.974    0.062   15.791    0.000
##   FA =~                                               
##     fa01              1.000                           
##     fa02              0.535    0.060    8.869    0.000
##     fa03              0.219    0.060    3.670    0.000
##     fa04              0.424    0.056    7.575    0.000
##     fa05              1.028    0.051   20.280    0.000
##     fa06              0.716    0.053   13.558    0.000
##     fa07              0.335    0.057    5.911    0.000
##     fa08              0.487    0.058    8.366    0.000
##     fa09              0.626    0.059   10.519    0.000
##     fa10              0.785    0.059   13.357    0.000
##   DE =~                                               
##     de01              1.000                           
##     de02              1.315    0.113   11.688    0.000
##     de03              1.183    0.111   10.668    0.000
##     de05              0.981    0.103    9.509    0.000
##     de06              1.276    0.116   11.019    0.000
##     de07              0.979    0.093   10.586    0.000
##     de08              1.185    0.102   11.579    0.000
##     de09              0.604    0.098    6.189    0.000
##     de10              1.377    0.116   11.853    0.000
##     de11              0.476    0.096    4.958    0.000
##   UN =~                                               
##     un01              1.000                           
##     un02              1.215    0.064   18.860    0.000
##     un03              0.817    0.068   11.959    0.000
##     un04              1.025    0.062   16.485    0.000
##     un05              1.142    0.063   18.233    0.000
##     un06              0.783    0.072   10.830    0.000
##     un07              1.040    0.068   15.336    0.000
##     un08              1.120    0.066   16.897    0.000
##     un09              1.090    0.071   15.404    0.000
##     un10              1.050    0.066   15.883    0.000
##     un11              1.192    0.069   17.382    0.000
##     un12              1.065    0.064   16.524    0.000
## 
## Covariances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   PR ~~                                               
##     CO                0.417    0.043    9.702    0.000
##     UT                0.479    0.045   10.634    0.000
##     FA                0.402    0.044    9.066    0.000
##     DE                0.423    0.045    9.495    0.000
##     UN                0.232    0.034    6.779    0.000
##   CO ~~                                               
##     UT                0.280    0.038    7.332    0.000
##     FA                0.355    0.044    8.018    0.000
##     DE                0.326    0.039    8.350    0.000
##     UN                0.171    0.033    5.125    0.000
##   UT ~~                                               
##     FA                0.331    0.043    7.706    0.000
##     DE                0.341    0.040    8.621    0.000
##     UN                0.187    0.034    5.560    0.000
##   FA ~~                                               
##     DE                0.366    0.043    8.534    0.000
##     UN                0.061    0.035    1.738    0.082
##   DE ~~                                               
##     UN                0.186    0.029    6.327    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##    .pr01              0.366    0.028   13.060    0.000
##    .pr02              0.619    0.041   14.916    0.000
##    .pr03              0.936    0.060   15.582    0.000
##    .pr04              1.071    0.068   15.711    0.000
##    .pr05              0.977    0.065   14.993    0.000
##    .pr06              0.751    0.050   14.902    0.000
##    .pr07              0.581    0.042   13.928    0.000
##    .pr08              0.390    0.028   13.953    0.000
##    .pr09              0.601    0.040   14.921    0.000
##    .pr10              0.805    0.053   15.208    0.000
##    .co01              0.526    0.040   13.135    0.000
##    .co02              0.573    0.041   13.824    0.000
##    .co03              0.780    0.052   15.010    0.000
##    .co04              1.045    0.068   15.460    0.000
##    .co05              0.481    0.039   12.355    0.000
##    .co06              0.763    0.053   14.429    0.000
##    .co08              0.957    0.062   15.462    0.000
##    .co09              0.536    0.040   13.296    0.000
##    .co10              0.763    0.053   14.505    0.000
##    .ut01              0.443    0.033   13.514    0.000
##    .ut02              0.333    0.027   12.266    0.000
##    .ut03              0.918    0.060   15.239    0.000
##    .ut04              0.959    0.063   15.322    0.000
##    .ut05              0.844    0.058   14.654    0.000
##    .ut06              0.528    0.038   13.844    0.000
##    .ut07              0.866    0.058   15.029    0.000
##    .ut08              0.674    0.046   14.788    0.000
##    .ut09              0.776    0.053   14.606    0.000
##    .ut11              1.107    0.073   15.183    0.000
##    .ut12              0.689    0.048   14.384    0.000
##    .fa01              0.393    0.036   11.016    0.000
##    .fa02              1.156    0.076   15.296    0.000
##    .fa03              1.245    0.079   15.664    0.000
##    .fa04              1.028    0.067   15.424    0.000
##    .fa05              0.348    0.034   10.153    0.000
##    .fa06              0.744    0.051   14.506    0.000
##    .fa07              1.092    0.070   15.551    0.000
##    .fa08              1.094    0.071   15.349    0.000
##    .fa09              1.071    0.071   15.086    0.000
##    .fa10              0.932    0.064   14.555    0.000
##    .de01              0.822    0.055   14.942    0.000
##    .de02              0.678    0.048   14.054    0.000
##    .de03              0.895    0.061   14.713    0.000
##    .de05              0.985    0.065   15.098    0.000
##    .de06              0.891    0.061   14.538    0.000
##    .de07              0.636    0.043   14.749    0.000
##    .de08              0.583    0.041   14.151    0.000
##    .de09              1.297    0.083   15.551    0.000
##    .de10              0.678    0.049   13.889    0.000
##    .de11              1.361    0.087   15.625    0.000
##    .un01              0.500    0.035   14.388    0.000
##    .un02              0.399    0.030   13.239    0.000
##    .un03              0.962    0.063   15.267    0.000
##    .un04              0.541    0.037   14.425    0.000
##    .un05              0.425    0.031   13.665    0.000
##    .un06              1.147    0.075   15.374    0.000
##    .un07              0.729    0.049   14.737    0.000
##    .un08              0.583    0.041   14.285    0.000
##    .un09              0.789    0.054   14.721    0.000
##    .un10              0.655    0.045   14.601    0.000
##    .un11              0.583    0.041   14.094    0.000
##    .un12              0.578    0.040   14.413    0.000
##     PR                0.605    0.059   10.207    0.000
##     CO                0.633    0.069    9.144    0.000
##     UT                0.659    0.066    9.942    0.000
##     FA                0.816    0.077   10.599    0.000
##     DE                0.377    0.058    6.490    0.000
##     UN                0.604    0.064    9.418    0.000

Fit measures:

kable(tibble(
  `Model 1` = c(
    "Chi-Squared",
    "DF",
    "p",
    "GFI",
    "AGFI",
    "CFI",
    "TLI",
    "SRMR",
    "RMSEA"
  ),
  Value = round(fitmeasures(
    model1,
    c(
      "chisq",
      "df",
      "pvalue",
      "gfi",
      "agfi",
      "cfi",
      "tli",
      "srmr",
      "rmsea"
    )
  ), 4)
))
Model 1 Value
Chi-Squared 6326.2235
DF 1814.0000
p 0.0000
GFI 0.6381
AGFI 0.6104
CFI 0.7096
TLI 0.6973
SRMR 0.1010
RMSEA 0.0709

Standardized solution:

smodel1 <- standardizedsolution(model1)

Loadings:

kable(
  smodel1 %>%
    filter(op == "=~"),
  col.names = c(
    "Factor",
    "",
    "Item",
    "Loading",
    "SE",
    "z",
    "p",
    "CI lower bound",
    "CI upper bound"
  ),
  digits = 3
)
Factor Item Loading SE z p CI lower bound CI upper bound
PR =~ pr01 0.789 0.020 39.913 0.000 0.751 0.828
PR =~ pr02 0.584 0.032 18.261 0.000 0.521 0.647
PR =~ pr03 0.296 0.043 6.854 0.000 0.211 0.381
PR =~ pr04 0.114 0.047 2.456 0.014 0.023 0.206
PR =~ pr05 0.565 0.033 17.164 0.000 0.501 0.630
PR =~ pr06 0.587 0.032 18.467 0.000 0.525 0.650
PR =~ pr07 0.728 0.024 30.723 0.000 0.682 0.775
PR =~ pr08 0.726 0.024 30.439 0.000 0.679 0.773
PR =~ pr09 0.583 0.032 18.186 0.000 0.520 0.645
PR =~ pr10 0.500 0.036 13.888 0.000 0.429 0.570
CO =~ co01 0.739 0.024 30.666 0.000 0.692 0.786
CO =~ co02 0.686 0.027 25.127 0.000 0.632 0.739
CO =~ co03 0.503 0.037 13.698 0.000 0.431 0.575
CO =~ co04 0.337 0.043 7.853 0.000 0.253 0.421
CO =~ co05 0.781 0.022 36.274 0.000 0.739 0.823
CO =~ co06 0.615 0.031 19.688 0.000 0.554 0.676
CO =~ co08 0.336 0.043 7.829 0.000 0.252 0.420
CO =~ co09 0.728 0.025 29.429 0.000 0.680 0.777
CO =~ co10 0.604 0.032 18.958 0.000 0.541 0.666
UT =~ ut01 0.773 0.021 37.597 0.000 0.733 0.814
UT =~ ut02 0.836 0.016 51.142 0.000 0.804 0.868
UT =~ ut03 0.500 0.036 13.954 0.000 0.430 0.570
UT =~ ut04 0.466 0.037 12.493 0.000 0.393 0.539
UT =~ ut05 0.649 0.028 22.945 0.000 0.593 0.704
UT =~ ut06 0.748 0.022 33.612 0.000 0.704 0.791
UT =~ ut07 0.568 0.033 17.378 0.000 0.504 0.632
UT =~ ut08 0.624 0.030 21.010 0.000 0.566 0.682
UT =~ ut09 0.657 0.028 23.611 0.000 0.602 0.711
UT =~ ut11 0.520 0.035 14.890 0.000 0.452 0.589
UT =~ ut12 0.690 0.026 26.662 0.000 0.639 0.741
FA =~ fa01 0.822 0.019 42.299 0.000 0.784 0.860
FA =~ fa02 0.410 0.040 10.123 0.000 0.330 0.489
FA =~ fa03 0.175 0.047 3.752 0.000 0.083 0.266
FA =~ fa04 0.353 0.042 8.337 0.000 0.270 0.436
FA =~ fa05 0.844 0.018 46.444 0.000 0.809 0.880
FA =~ fa06 0.600 0.032 18.680 0.000 0.537 0.663
FA =~ fa07 0.279 0.044 6.264 0.000 0.191 0.366
FA =~ fa08 0.388 0.041 9.407 0.000 0.307 0.469
FA =~ fa09 0.479 0.038 12.693 0.000 0.405 0.553
FA =~ fa10 0.592 0.033 18.218 0.000 0.528 0.656
DE =~ de01 0.561 0.033 16.808 0.000 0.495 0.626
DE =~ de02 0.700 0.026 27.265 0.000 0.650 0.751
DE =~ de03 0.609 0.031 19.717 0.000 0.548 0.670
DE =~ de05 0.519 0.035 14.677 0.000 0.450 0.588
DE =~ de06 0.639 0.029 21.837 0.000 0.582 0.696
DE =~ de07 0.602 0.031 19.273 0.000 0.541 0.663
DE =~ de08 0.690 0.026 26.215 0.000 0.638 0.741
DE =~ de09 0.310 0.043 7.191 0.000 0.225 0.394
DE =~ de10 0.716 0.025 29.002 0.000 0.668 0.765
DE =~ de11 0.243 0.045 5.436 0.000 0.155 0.331
UN =~ un01 0.740 0.022 33.462 0.000 0.696 0.783
UN =~ un02 0.831 0.016 52.491 0.000 0.800 0.862
UN =~ un03 0.544 0.033 16.332 0.000 0.478 0.609
UN =~ un04 0.735 0.022 32.798 0.000 0.691 0.779
UN =~ un05 0.806 0.018 45.760 0.000 0.771 0.840
UN =~ un06 0.494 0.036 13.895 0.000 0.425 0.564
UN =~ un07 0.687 0.025 27.059 0.000 0.638 0.737
UN =~ un08 0.752 0.021 35.289 0.000 0.710 0.794
UN =~ un09 0.690 0.025 27.358 0.000 0.641 0.740
UN =~ un10 0.710 0.024 29.592 0.000 0.663 0.757
UN =~ un11 0.772 0.020 38.620 0.000 0.732 0.811
UN =~ un12 0.737 0.022 33.023 0.000 0.693 0.780

Covariances:

kable(
  smodel1 %>% 
    filter(op == "~~" & lhs != rhs),
  col.names = c("Factor", "", "Factor", "Covariance", "SE", "z", "p", "CI lower bound", "CI upper bound"),
  digits = 3
)
Factor Factor Covariance SE z p CI lower bound CI upper bound
PR ~~ CO 0.674 0.032 21.123 0.000 0.611 0.736
PR ~~ UT 0.758 0.025 29.745 0.000 0.708 0.808
PR ~~ FA 0.572 0.037 15.251 0.000 0.498 0.645
PR ~~ DE 0.886 0.019 47.788 0.000 0.849 0.922
PR ~~ UN 0.383 0.043 8.811 0.000 0.298 0.469
CO ~~ UT 0.434 0.042 10.255 0.000 0.351 0.517
CO ~~ FA 0.493 0.041 12.022 0.000 0.413 0.574
CO ~~ DE 0.667 0.033 20.416 0.000 0.603 0.731
CO ~~ UN 0.276 0.047 5.929 0.000 0.185 0.367
UT ~~ FA 0.451 0.042 10.813 0.000 0.369 0.532
UT ~~ DE 0.684 0.030 22.435 0.000 0.624 0.744
UT ~~ UN 0.296 0.045 6.570 0.000 0.207 0.384
FA ~~ DE 0.659 0.033 19.845 0.000 0.594 0.724
FA ~~ UN 0.087 0.050 1.762 0.078 -0.010 0.185
DE ~~ UN 0.389 0.044 8.920 0.000 0.304 0.475

Residuals:

kable(
  smodel1 %>% 
    filter(op == "~~" & lhs == rhs)%>% 
    select(-(2:3)),
  col.names = c("Item", "Residual", "SE", "z", "p", "CI lower bound", "CI upper bound"),
  digits = 3
)
Item Residual SE z p CI lower bound CI upper bound
pr01 0.377 0.031 12.076 0 0.316 0.438
pr02 0.659 0.037 17.653 0 0.586 0.732
pr03 0.912 0.026 35.640 0 0.862 0.962
pr04 0.987 0.011 92.749 0 0.966 1.008
pr05 0.681 0.037 18.291 0 0.608 0.754
pr06 0.655 0.037 17.542 0 0.582 0.728
pr07 0.470 0.035 13.609 0 0.402 0.537
pr08 0.473 0.035 13.667 0 0.405 0.541
pr09 0.661 0.037 17.694 0 0.587 0.734
pr10 0.750 0.036 20.839 0 0.680 0.821
co01 0.454 0.036 12.730 0 0.384 0.523
co02 0.530 0.037 14.153 0 0.456 0.603
co03 0.747 0.037 20.238 0 0.675 0.820
co04 0.887 0.029 30.728 0 0.830 0.943
co05 0.390 0.034 11.593 0 0.324 0.456
co06 0.622 0.038 16.181 0 0.546 0.697
co08 0.887 0.029 30.806 0 0.831 0.944
co09 0.469 0.036 13.014 0 0.399 0.540
co10 0.636 0.038 16.536 0 0.560 0.711
ut01 0.402 0.032 12.630 0 0.340 0.464
ut02 0.301 0.027 11.006 0 0.247 0.354
ut03 0.750 0.036 20.907 0 0.679 0.820
ut04 0.783 0.035 22.500 0 0.715 0.851
ut05 0.579 0.037 15.774 0 0.507 0.651
ut06 0.441 0.033 13.251 0 0.376 0.506
ut07 0.678 0.037 18.290 0 0.605 0.751
ut08 0.611 0.037 16.492 0 0.538 0.683
ut09 0.568 0.037 15.554 0 0.497 0.640
ut11 0.729 0.036 20.063 0 0.658 0.801
ut12 0.524 0.036 14.683 0 0.454 0.594
fa01 0.325 0.032 10.177 0 0.262 0.387
fa02 0.832 0.033 25.070 0 0.767 0.897
fa03 0.969 0.016 59.581 0 0.938 1.001
fa04 0.875 0.030 29.210 0 0.816 0.934
fa05 0.287 0.031 9.357 0 0.227 0.347
fa06 0.640 0.039 16.624 0 0.565 0.716
fa07 0.922 0.025 37.218 0 0.874 0.971
fa08 0.849 0.032 26.527 0 0.787 0.912
fa09 0.770 0.036 21.268 0 0.699 0.841
fa10 0.649 0.038 16.872 0 0.574 0.725
de01 0.686 0.037 18.318 0 0.612 0.759
de02 0.510 0.036 14.162 0 0.439 0.580
de03 0.629 0.038 16.722 0 0.555 0.703
de05 0.731 0.037 19.910 0 0.659 0.803
de06 0.592 0.037 15.832 0 0.519 0.665
de07 0.637 0.038 16.934 0 0.564 0.711
de08 0.524 0.036 14.436 0 0.453 0.595
de09 0.904 0.027 33.919 0 0.852 0.956
de10 0.487 0.035 13.746 0 0.417 0.556
de11 0.941 0.022 43.330 0 0.898 0.984
un01 0.453 0.033 13.854 0 0.389 0.517
un02 0.309 0.026 11.747 0 0.258 0.361
un03 0.705 0.036 19.471 0 0.634 0.775
un04 0.460 0.033 13.962 0 0.395 0.524
un05 0.350 0.028 12.343 0 0.295 0.406
un06 0.756 0.035 21.495 0 0.687 0.825
un07 0.528 0.035 15.106 0 0.459 0.596
un08 0.435 0.032 13.574 0 0.372 0.498
un09 0.524 0.035 15.035 0 0.455 0.592
un10 0.496 0.034 14.549 0 0.429 0.563
un11 0.405 0.031 13.125 0 0.344 0.465
un12 0.458 0.033 13.925 0 0.393 0.522
PR 1.000 0.000 NA NA 1.000 1.000
CO 1.000 0.000 NA NA 1.000 1.000
UT 1.000 0.000 NA NA 1.000 1.000
FA 1.000 0.000 NA NA 1.000 1.000
DE 1.000 0.000 NA NA 1.000 1.000
UN 1.000 0.000 NA NA 1.000 1.000

Visualization:

semPaths(model1, "std")

Model with general factor

Model:

mdl2 <- "
PR =~ pr01 + pr02 + pr03 + pr04 + pr05 + pr06 + pr07 + pr08 + pr09 + pr10
CO =~ co01 + co02 + co03 + co04 + co05 + co06 + co08 + co09 + co10
UT =~ ut01 + ut02 + ut03 + ut04 + ut05 + ut06 + ut07 + ut08 + ut09 + ut11 + ut12
FA =~ fa01 + fa02 + fa03 + fa04 + fa05 + fa06 + fa07 + fa08 + fa09 + fa10
DE =~ de01 + de02 + de03 + de05 + de06 + de07 + de08 + de09 + de10 + de11
UN =~ un01 + un02 + un03 + un04 + un05 + un06 + un07 + un08 + un09 + un10 + un11 + un12
DigTrust =~ PR + CO + UT + FA + DE + UN
"
model2 <- cfa(mdl2, taia %>% select(all_of(taia_items)))
summary(model2)
## lavaan 0.6-8 ended normally after 44 iterations
## 
##   Estimator                                         ML
##   Optimization method                           NLMINB
##   Number of model parameters                       130
##                                                       
##   Number of observations                           495
##                                                       
## Model Test User Model:
##                                                       
##   Test statistic                              6381.193
##   Degrees of freedom                              1823
##   P-value (Chi-square)                           0.000
## 
## Parameter Estimates:
## 
##   Standard errors                             Standard
##   Information                                 Expected
##   Information saturated (h1) model          Structured
## 
## Latent Variables:
##                    Estimate  Std.Err  z-value  P(>|z|)
##   PR =~                                               
##     pr01              1.000                           
##     pr02              0.732    0.055   13.227    0.000
##     pr03              0.389    0.061    6.409    0.000
##     pr04              0.160    0.063    2.533    0.011
##     pr05              0.882    0.069   12.845    0.000
##     pr06              0.797    0.061   13.006    0.000
##     pr07              1.049    0.061   17.137    0.000
##     pr08              0.846    0.050   16.877    0.000
##     pr09              0.719    0.055   13.186    0.000
##     pr10              0.661    0.060   10.962    0.000
##   CO =~                                               
##     co01              1.000                           
##     co02              0.894    0.062   14.491    0.000
##     co03              0.652    0.061   10.699    0.000
##     co04              0.473    0.065    7.263    0.000
##     co05              1.088    0.066   16.548    0.000
##     co06              0.862    0.066   13.089    0.000
##     co08              0.435    0.062    6.976    0.000
##     co09              0.977    0.063   15.442    0.000
##     co10              0.834    0.065   12.798    0.000
##   UT =~                                               
##     ut01              1.000                           
##     ut02              1.080    0.055   19.757    0.000
##     ut03              0.674    0.062   10.910    0.000
##     ut04              0.635    0.062   10.237    0.000
##     ut05              0.972    0.065   14.837    0.000
##     ut06              1.007    0.058   17.336    0.000
##     ut07              0.791    0.062   12.699    0.000
##     ut08              0.807    0.057   14.089    0.000
##     ut09              0.946    0.063   14.941    0.000
##     ut11              0.790    0.068   11.534    0.000
##     ut12              0.973    0.062   15.774    0.000
##   FA =~                                               
##     fa01              1.000                           
##     fa02              0.522    0.060    8.760    0.000
##     fa03              0.204    0.059    3.452    0.001
##     fa04              0.407    0.055    7.352    0.000
##     fa05              1.017    0.050   20.447    0.000
##     fa06              0.704    0.052   13.544    0.000
##     fa07              0.323    0.056    5.749    0.000
##     fa08              0.475    0.058    8.239    0.000
##     fa09              0.616    0.059   10.488    0.000
##     fa10              0.780    0.058   13.496    0.000
##   DE =~                                               
##     de01              1.000                           
##     de02              1.314    0.113   11.628    0.000
##     de03              1.176    0.111   10.576    0.000
##     de05              1.006    0.104    9.645    0.000
##     de06              1.267    0.116   10.914    0.000
##     de07              0.989    0.093   10.609    0.000
##     de08              1.188    0.103   11.539    0.000
##     de09              0.623    0.098    6.342    0.000
##     de10              1.371    0.117   11.764    0.000
##     de11              0.475    0.096    4.934    0.000
##   UN =~                                               
##     un01              1.000                           
##     un02              1.212    0.064   18.935    0.000
##     un03              0.811    0.068   11.917    0.000
##     un04              1.022    0.062   16.530    0.000
##     un05              1.140    0.062   18.326    0.000
##     un06              0.780    0.072   10.831    0.000
##     un07              1.035    0.067   15.346    0.000
##     un08              1.118    0.066   16.974    0.000
##     un09              1.085    0.070   15.412    0.000
##     un10              1.046    0.066   15.902    0.000
##     un11              1.188    0.068   17.430    0.000
##     un12              1.061    0.064   16.562    0.000
##   DigTrust =~                                         
##     PR                1.000                           
##     CO                0.746    0.061   12.327    0.000
##     UT                0.818    0.060   13.693    0.000
##     FA                0.781    0.064   12.133    0.000
##     DE                0.777    0.066   11.697    0.000
##     UN                0.408    0.053    7.651    0.000
## 
## Variances:
##                    Estimate  Std.Err  z-value  P(>|z|)
##    .pr01              0.369    0.028   13.031    0.000
##    .pr02              0.616    0.041   14.883    0.000
##    .pr03              0.935    0.060   15.576    0.000
##    .pr04              1.070    0.068   15.709    0.000
##    .pr05              0.966    0.065   14.947    0.000
##    .pr06              0.763    0.051   14.921    0.000
##    .pr07              0.573    0.041   13.836    0.000
##    .pr08              0.393    0.028   13.938    0.000
##    .pr09              0.599    0.040   14.890    0.000
##    .pr10              0.810    0.053   15.208    0.000
##    .co01              0.528    0.040   13.119    0.000
##    .co02              0.578    0.042   13.832    0.000
##    .co03              0.775    0.052   14.982    0.000
##    .co04              1.037    0.067   15.438    0.000
##    .co05              0.485    0.039   12.362    0.000
##    .co06              0.759    0.053   14.391    0.000
##    .co08              0.959    0.062   15.463    0.000
##    .co09              0.539    0.041   13.290    0.000
##    .co10              0.761    0.053   14.482    0.000
##    .ut01              0.442    0.033   13.486    0.000
##    .ut02              0.336    0.027   12.276    0.000
##    .ut03              0.925    0.061   15.248    0.000
##    .ut04              0.959    0.063   15.318    0.000
##    .ut05              0.836    0.057   14.615    0.000
##    .ut06              0.528    0.038   13.826    0.000
##    .ut07              0.864    0.058   15.017    0.000
##    .ut08              0.673    0.046   14.776    0.000
##    .ut09              0.775    0.053   14.590    0.000
##    .ut11              1.106    0.073   15.176    0.000
##    .ut12              0.690    0.048   14.373    0.000
##    .fa01              0.375    0.035   10.619    0.000
##    .fa02              1.162    0.076   15.307    0.000
##    .fa03              1.250    0.080   15.672    0.000
##    .fa04              1.036    0.067   15.443    0.000
##    .fa05              0.348    0.035   10.076    0.000
##    .fa06              0.748    0.052   14.517    0.000
##    .fa07              1.097    0.070   15.560    0.000
##    .fa08              1.100    0.072   15.361    0.000
##    .fa09              1.074    0.071   15.090    0.000
##    .fa10              0.927    0.064   14.529    0.000
##    .de01              0.823    0.055   14.925    0.000
##    .de02              0.681    0.049   14.028    0.000
##    .de03              0.904    0.061   14.713    0.000
##    .de05              0.968    0.064   15.039    0.000
##    .de06              0.902    0.062   14.545    0.000
##    .de07              0.630    0.043   14.698    0.000
##    .de08              0.583    0.041   14.109    0.000
##    .de09              1.288    0.083   15.533    0.000
##    .de10              0.687    0.049   13.891    0.000
##    .de11              1.361    0.087   15.623    0.000
##    .un01              0.497    0.035   14.367    0.000
##    .un02              0.399    0.030   13.228    0.000
##    .un03              0.966    0.063   15.272    0.000
##    .un04              0.541    0.038   14.422    0.000
##    .un05              0.423    0.031   13.641    0.000
##    .un06              1.148    0.075   15.374    0.000
##    .un07              0.732    0.050   14.740    0.000
##    .un08              0.581    0.041   14.271    0.000
##    .un09              0.792    0.054   14.725    0.000
##    .un10              0.657    0.045   14.604    0.000
##    .un11              0.584    0.041   14.091    0.000
##    .un12              0.578    0.040   14.412    0.000
##    .PR                0.051    0.017    2.954    0.003
##    .CO                0.324    0.039    8.231    0.000
##    .UT                0.290    0.033    8.734    0.000
##    .FA                0.498    0.051    9.744    0.000
##    .DE                0.043    0.012    3.438    0.001
##    .UN                0.516    0.055    9.336    0.000
##     DigTrust          0.552    0.058    9.531    0.000
kable(tibble(
  `Model 2` = c(
    "Chi-Squared",
    "DF",
    "p",
    "GFI",
    "AGFI",
    "CFI",
    "TLI",
    "SRMR",
    "RMSEA"
  ),
  Value = round(fitmeasures(
    model2,
    c(
      "chisq",
      "df",
      "pvalue",
      "gfi",
      "agfi",
      "cfi",
      "tli",
      "srmr",
      "rmsea"
    )
  ), 4)
))
Model 2 Value
Chi-Squared 6381.1932
DF 1823.0000
p 0.0000
GFI 0.6329
AGFI 0.6068
CFI 0.7067
TLI 0.6957
SRMR 0.1029
RMSEA 0.0711
semPaths(model2, "std")

Validation

TAIA total score

taia %>% 
  select(id, all_of(taia_items)) %>% 
  pivot_longer(all_of(taia_items),
               names_to = "subscale",
               values_to = "score") %>% 
  mutate(subscale = str_remove_all(subscale, "[:digit:]{2}") %>% toupper()) %>% 
  group_by(id, subscale) %>% 
  summarise(total_score = sum(score)) %>% 
  pivot_wider(id_cols = id,
              names_from = subscale,
              values_from = total_score) %>% 
  full_join(taia) -> taia
## `summarise()` regrouping output by 'id' (override with `.groups` argument)
## Joining, by = "id"
clrs <-
  c("darkred",
    "chocolate3",
    "goldenrod3",
    "darkgreen",
    "darkblue",
    "purple4")

Correlations with General Trust Scale

taia %>% 
  pivot_longer(cols = c("PR", "CO", "UT", "FA", "DE", "UN"),
               names_to = "subscale",
               values_to = "score") %>%
  mutate(subscale = factor(subscale, levels = c("PR", "CO", "UT", "FA", "DE", "UN"))) -> taia_l
taia_l %>% 
  ggplot(aes(score, gt_score, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  scale_color_manual(values = clrs) +
  guides(color = FALSE) +
  labs(x = "TAIA subscale total score",
       y = "General Trust Scale total score",
       title = "Corelations between General Trust and TAIA subscales") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'

cor.test(taia$PR, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$PR and taia$gt_score
## t = 3.1872, df = 493, p-value = 0.001528
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.05463758 0.22737163
## sample estimates:
##       cor 
## 0.1420861
cor.test(taia$CO, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$CO and taia$gt_score
## t = 3.842, df = 493, p-value = 0.000138
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.08362567 0.25480562
## sample estimates:
##       cor 
## 0.1705018
cor.test(taia$UT, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UT and taia$gt_score
## t = 2.4679, df = 493, p-value = 0.01393
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.02255584 0.19668679
## sample estimates:
##      cor 
## 0.110469
cor.test(taia$FA, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$FA and taia$gt_score
## t = 2.0938, df = 493, p-value = 0.03678
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.005800447 0.180524218
## sample estimates:
##       cor 
## 0.0938852
cor.test(taia$DE, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$DE and taia$gt_score
## t = 4.1369, df = 493, p-value = 4.139e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.09659152 0.26698780
## sample estimates:
##      cor 
## 0.183165
cor.test(taia$UN, taia$gt_score)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UN and taia$gt_score
## t = 3.5643, df = 493, p-value = 0.0004003
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.07136383 0.24323469
## sample estimates:
##       cor 
## 0.1584997

Correlations with questions

taia_l %>% 
  ggplot(aes(score, n_dighelp, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Number of digital helpers",
       title = "Correlation TAIA subscales with number of digital helpers") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 948 rows containing non-finite values (stat_smooth).
## Warning: Removed 948 rows containing missing values (geom_point).

cor.test(taia$PR, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$PR, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$PR and taia$n_dighelp
## S = 5561417, p-value = 0.01861
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1281319
cor.test(taia$CO, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$CO, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$CO and taia$n_dighelp
## S = 6618523, p-value = 0.4916
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##         rho 
## -0.03759163
cor.test(taia$UT, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$UT, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UT and taia$n_dighelp
## S = 5620719, p-value = 0.02917
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##      rho 
## 0.118835
cor.test(taia$FA, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$FA, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$FA and taia$n_dighelp
## S = 6614475, p-value = 0.4989
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##         rho 
## -0.03695705
cor.test(taia$DE, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$DE, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$DE and taia$n_dighelp
## S = 5705718, p-value = 0.05298
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1055096
cor.test(taia$UN, taia$n_dighelp, method = "sp")
## Warning in cor.test.default(taia$UN, taia$n_dighelp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UN and taia$n_dighelp
## S = 5912050, p-value = 0.1803
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.0731627
taia_l %>%
  ggplot(aes(score, e_dighelp, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Estimate of dealing with digital helpers experience",
       title = "Correlation TAIA subscales with expirience of dealing with digital helpers") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 948 rows containing non-finite values (stat_smooth).
## Warning: Removed 948 rows containing missing values (geom_point).

cor.test(taia$PR, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$PR and taia$e_dighelp
## t = 6.7852, df = 335, p-value = 5.27e-11
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.2500476 0.4381609
## sample estimates:
##       cor 
## 0.3475971
cor.test(taia$CO, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$CO and taia$e_dighelp
## t = 4.0996, df = 335, p-value = 5.199e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1144032 0.3179773
## sample estimates:
##      cor 
## 0.218567
cor.test(taia$UT, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UT and taia$e_dighelp
## t = 5.5088, df = 335, p-value = 7.21e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1871349 0.3832429
## sample estimates:
##      cor 
## 0.288208
cor.test(taia$FA, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$FA and taia$e_dighelp
## t = 4.1342, df = 335, p-value = 4.507e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1162249 0.3196358
## sample estimates:
##       cor 
## 0.2203243
cor.test(taia$DE, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$DE and taia$e_dighelp
## t = 5.7293, df = 335, p-value = 2.248e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1982204 0.3930214
## sample estimates:
##       cor 
## 0.2987294
cor.test(taia$UN, taia$e_dighelp)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UN and taia$e_dighelp
## t = 1.7091, df = 335, p-value = 0.08836
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.01400204  0.19784231
## sample estimates:
##        cor 
## 0.09297223
taia_l %>% 
  ggplot(aes(score, n_socnet, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Number of social networks and social media",
       title = "Correlation TAIA subscales with number of social networks and social media") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 360 rows containing non-finite values (stat_smooth).
## Warning: Removed 360 rows containing missing values (geom_point).

cor.test(taia$PR, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$PR, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$PR and taia$n_socnet
## S = 12147347, p-value = 0.01685
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1145436
cor.test(taia$CO, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$CO, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$CO and taia$n_socnet
## S = 14058484, p-value = 0.6065
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##         rho 
## -0.02476493
cor.test(taia$UT, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$UT, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UT and taia$n_socnet
## S = 11573855, p-value = 0.001069
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1563471
cor.test(taia$FA, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$FA, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$FA and taia$n_socnet
## S = 12379302, p-value = 0.04181
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## 0.09763564
cor.test(taia$DE, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$DE, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$DE and taia$n_socnet
## S = 11425218, p-value = 0.0004627
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1671817
cor.test(taia$UN, taia$n_socnet, method = "sp")
## Warning in cor.test.default(taia$UN, taia$n_socnet, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UN and taia$n_socnet
## S = 12007801, p-value = 0.009219
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1247154
taia_l %>% 
  ggplot(aes(score, f_socnet, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Frequency of social networks and social media use",
       title = "Correlation TAIA subscales with frequency of social networks and social media use") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 360 rows containing non-finite values (stat_smooth).
## Warning: Removed 360 rows containing missing values (geom_point).

cor.test(taia$PR, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$PR and taia$f_socnet
## t = 1.4848, df = 433, p-value = 0.1383
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.02299864  0.16409771
## sample estimates:
##        cor 
## 0.07117555
cor.test(taia$CO, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$CO and taia$f_socnet
## t = 0.83383, df = 433, p-value = 0.4048
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.05418487  0.13355691
## sample estimates:
##       cor 
## 0.0400394
cor.test(taia$UT, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UT and taia$f_socnet
## t = -0.18344, df = 433, p-value = 0.8545
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.10275052  0.08527558
## sample estimates:
##          cor 
## -0.008815392
cor.test(taia$FA, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$FA and taia$f_socnet
## t = 0.30431, df = 433, p-value = 0.761
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.07950679  0.10849394
## sample estimates:
##        cor 
## 0.01462281
cor.test(taia$DE, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$DE and taia$f_socnet
## t = 0.51348, df = 433, p-value = 0.6079
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.06951288  0.11841428
## sample estimates:
##        cor 
## 0.02466864
cor.test(taia$UN, taia$f_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UN and taia$f_socnet
## t = -0.29625, df = 433, p-value = 0.7672
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.10811106  0.07989175
## sample estimates:
##         cor 
## -0.01423547
taia_l %>% 
  ggplot(aes(score, e_socnet, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Estimate of dealing with recommender systems experience",
       title = "Correlation TAIA subscales with experience of dealing with recommender systems") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 360 rows containing non-finite values (stat_smooth).
## Warning: Removed 360 rows containing missing values (geom_point).

cor.test(taia$PR, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$PR and taia$e_socnet
## t = 4.6683, df = 433, p-value = 4.056e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1275089 0.3066146
## sample estimates:
##       cor 
## 0.2189049
cor.test(taia$CO, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$CO and taia$e_socnet
## t = 5.3414, df = 433, p-value = 1.493e-07
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1583093 0.3348224
## sample estimates:
##       cor 
## 0.2486289
cor.test(taia$UT, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UT and taia$e_socnet
## t = 4.0939, df = 433, p-value = 5.061e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1008503 0.2819433
## sample estimates:
##       cor 
## 0.1930402
cor.test(taia$FA, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$FA and taia$e_socnet
## t = 2.5727, df = 433, p-value = 0.01042
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.02901732 0.21425142
## sample estimates:
##       cor 
## 0.1227028
cor.test(taia$DE, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$DE and taia$e_socnet
## t = 5.7293, df = 433, p-value = 1.89e-08
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1758227 0.3507217
## sample estimates:
##       cor 
## 0.2654548
cor.test(taia$UN, taia$e_socnet)
## 
##  Pearson's product-moment correlation
## 
## data:  taia$UN and taia$e_socnet
## t = 1.7866, df = 433, p-value = 0.0747
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.008545219  0.178131408
## sample estimates:
##       cor 
## 0.0855438

Self driving cars and education AI

taia %>% 
  mutate_at(vars(selfdrexp, selfdrsafe, eduaiexp),
            function(x) ifelse(x < 0, NA, x)) -> taia
taia %>% 
  pivot_longer(cols = c("PR", "CO", "UT", "FA", "DE", "UN"),
               names_to = "subscale",
               values_to = "score") %>% 
  mutate(subscale = factor(subscale, levels = c("PR", "CO", "UT", "FA", "DE", "UN"))) %>% 
  ggplot(aes(score, selfdrexp, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Estimate of selfdriving car experience",
       title = "Correlation TAIA subscales with selfdriving car experience") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 2892 rows containing non-finite values (stat_smooth).
## Warning: Removed 2892 rows containing missing values (geom_point).

cor.test(taia$PR, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$PR, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$PR and taia$selfdrexp
## S = 265.3, p-value = 0.3702
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.2711565
cor.test(taia$CO, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$CO, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$CO and taia$selfdrexp
## S = 418.25, p-value = 0.627
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.1490473
cor.test(taia$UT, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$UT, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UT and taia$selfdrexp
## S = 175.48, p-value = 0.06984
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.5179022
cor.test(taia$FA, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$FA, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$FA and taia$selfdrexp
## S = 272.56, p-value = 0.4077
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.2512199
cor.test(taia$DE, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$DE, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$DE and taia$selfdrexp
## S = 326.24, p-value = 0.7359
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1037321
cor.test(taia$UN, taia$selfdrexp, method = "sp")
## Warning in cor.test.default(taia$UN, taia$selfdrexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UN and taia$selfdrexp
## S = 358.61, p-value = 0.9617
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## 0.01481886
taia %>% 
  pivot_longer(cols = c("PR", "CO", "UT", "FA", "DE", "UN"),
               names_to = "subscale",
               values_to = "score") %>% 
  mutate(subscale = factor(subscale, levels = c("PR", "CO", "UT", "FA", "DE", "UN"))) %>% 
  ggplot(aes(score, selfdrsafe, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Estimate of selfdriving car safe",
       title = "Correlation TAIA subscales with selfdriving car safe") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 2892 rows containing non-finite values (stat_smooth).
## Warning: Removed 2892 rows containing missing values (geom_point).

cor.test(taia$PR, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$PR, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$PR and taia$selfdrsafe
## S = 372.22, p-value = 0.9417
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##         rho 
## -0.02257133
cor.test(taia$CO, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$CO, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$CO and taia$selfdrsafe
## S = 323.96, p-value = 0.7205
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1099992
cor.test(taia$UT, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$UT, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UT and taia$selfdrsafe
## S = 301.67, p-value = 0.576
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.1712239
cor.test(taia$FA, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$FA, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$FA and taia$selfdrsafe
## S = 217.35, p-value = 0.1723
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.4028841
cor.test(taia$DE, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$DE, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$DE and taia$selfdrsafe
## S = 352.98, p-value = 0.9218
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## 0.03026276
cor.test(taia$UN, taia$selfdrsafe, method = "sp")
## Warning in cor.test.default(taia$UN, taia$selfdrsafe, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UN and taia$selfdrsafe
## S = 450.47, p-value = 0.4345
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##        rho 
## -0.2375627
taia %>% 
  pivot_longer(cols = c("PR", "CO", "UT", "FA", "DE", "UN"),
               names_to = "subscale",
               values_to = "score") %>% 
  mutate(subscale = factor(subscale, levels = c("PR", "CO", "UT", "FA", "DE", "UN"))) %>% 
  ggplot(aes(score, eduaiexp, color = subscale)) +
  geom_point(alpha = .3) +
  geom_smooth(method = "lm") +
  facet_wrap(~ subscale) +
  guides(color = FALSE) +
  scale_color_manual(values = clrs) +
  labs(x = "TAIA subscales total score",
       y = "Estimate of dealing with education AI experience",
       title = "Correlation TAIA subscales with experience of dealing with education AI") +
  theme(plot.title = element_text(hjust = .5))
## `geom_smooth()` using formula 'y ~ x'
## Warning: Removed 2298 rows containing non-finite values (stat_smooth).
## Warning: Removed 2298 rows containing missing values (geom_point).

cor.test(taia$PR, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$PR, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$PR and taia$eduaiexp
## S = 136920, p-value = 5.31e-06
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.4152137
cor.test(taia$CO, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$CO, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$CO and taia$eduaiexp
## S = 145289, p-value = 3.687e-05
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.3794657
cor.test(taia$UT, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$UT, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UT and taia$eduaiexp
## S = 142744, p-value = 2.094e-05
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.3903391
cor.test(taia$FA, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$FA, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$FA and taia$eduaiexp
## S = 168570, p-value = 0.002786
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.2800356
cor.test(taia$DE, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$DE, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$DE and taia$eduaiexp
## S = 112949, p-value = 5.1e-09
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.5175924
cor.test(taia$UN, taia$eduaiexp, method = "sp")
## Warning in cor.test.default(taia$UN, taia$eduaiexp, method = "sp"): Cannot
## compute exact p-value with ties
## 
##  Spearman's rank correlation rho
## 
## data:  taia$UN and taia$eduaiexp
## S = 159518, p-value = 0.0006156
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
##       rho 
## 0.3186946